From: zhengbin zhengbin13@huawei.com

[ Upstream commit 713f871b30a66dc4daff4d17b760c9916aaaf2e1 ]

In media_device_register_entity, if media_graph_walk_init fails, need to free the previously memory.

Reported-by: Hulk Robot hulkci@huawei.com Signed-off-by: zhengbin zhengbin13@huawei.com Signed-off-by: Sakari Ailus sakari.ailus@linux.intel.com Signed-off-by: Mauro Carvalho Chehab mchehab+samsung@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/media/media-device.c | 65 ++++++++++++++++++------------------ 1 file changed, 33 insertions(+), 32 deletions(-)

diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index ed518b1f82e4..d04ed438a45d 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -568,6 +568,38 @@ static void media_device_release(struct media_devnode *devnode) dev_dbg(devnode->parent, "Media device released\n"); }

+static void __media_device_unregister_entity(struct media_entity *entity) +{ + struct media_device *mdev = entity->graph_obj.mdev; + struct media_link *link, *tmp; + struct media_interface *intf; + unsigned int i; + + ida_free(&mdev->entity_internal_idx, entity->internal_idx); + + /* Remove all interface links pointing to this entity */ + list_for_each_entry(intf, &mdev->interfaces, graph_obj.list) { + list_for_each_entry_safe(link, tmp, &intf->links, list) { + if (link->entity == entity) + __media_remove_intf_link(link); + } + } + + /* Remove all data links that belong to this entity */ + __media_entity_remove_links(entity); + + /* Remove all pads that belong to this entity */ + for (i = 0; i < entity->num_pads; i++) + media_gobj_destroy(&entity->pads[i].graph_obj); + + /* Remove the entity */ + media_gobj_destroy(&entity->graph_obj); + + /* invoke entity_notify callbacks to handle entity removal?? */ + + entity->graph_obj.mdev = NULL; +} + /** * media_device_register_entity - Register an entity with a media device * @mdev: The media device @@ -625,6 +657,7 @@ int __must_check media_device_register_entity(struct media_device *mdev, */ ret = media_graph_walk_init(&new, mdev); if (ret) { + __media_device_unregister_entity(entity); mutex_unlock(&mdev->graph_mutex); return ret; } @@ -637,38 +670,6 @@ int __must_check media_device_register_entity(struct media_device *mdev, } EXPORT_SYMBOL_GPL(media_device_register_entity);

-static void __media_device_unregister_entity(struct media_entity *entity) -{ - struct media_device *mdev = entity->graph_obj.mdev; - struct media_link *link, *tmp; - struct media_interface *intf; - unsigned int i; - - ida_free(&mdev->entity_internal_idx, entity->internal_idx); - - /* Remove all interface links pointing to this entity */ - list_for_each_entry(intf, &mdev->interfaces, graph_obj.list) { - list_for_each_entry_safe(link, tmp, &intf->links, list) { - if (link->entity == entity) - __media_remove_intf_link(link); - } - } - - /* Remove all data links that belong to this entity */ - __media_entity_remove_links(entity); - - /* Remove all pads that belong to this entity */ - for (i = 0; i < entity->num_pads; i++) - media_gobj_destroy(&entity->pads[i].graph_obj); - - /* Remove the entity */ - media_gobj_destroy(&entity->graph_obj); - - /* invoke entity_notify callbacks to handle entity removal?? */ - - entity->graph_obj.mdev = NULL; -} - void media_device_unregister_entity(struct media_entity *entity) { struct media_device *mdev = entity->graph_obj.mdev;

From: Miaoqing Pan miaoqing@codeaurora.org

[ Upstream commit c5329b2d5b8b4e41be14d31ee8505b4f5607bf9b ]

If firmware reports rate_max > WMI_TPC_RATE_MAX(WMI_TPC_FINAL_RATE_MAX) or num_tx_chain > WMI_TPC_TX_N_CHAIN, it will cause array out-of-bounds access, so print a warning and reset to avoid memory corruption.

Tested HW: QCA9984 Tested FW: 10.4-3.9.0.2-00035

Signed-off-by: Miaoqing Pan miaoqing@codeaurora.org Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/net/wireless/ath/ath10k/debug.c | 2 +- drivers/net/wireless/ath/ath10k/wmi.c | 49 ++++++++++++++++--------- 2 files changed, 32 insertions(+), 19 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/debug.c b/drivers/net/wireless/ath/ath10k/debug.c index 0baaad90b8d1..aa333110eaba 100644 --- a/drivers/net/wireless/ath/ath10k/debug.c +++ b/drivers/net/wireless/ath/ath10k/debug.c @@ -1521,7 +1521,7 @@ static void ath10k_tpc_stats_print(struct ath10k_tpc_stats *tpc_stats, *len += scnprintf(buf + *len, buf_len - *len, "No. Preamble Rate_code ");

- for (i = 0; i < WMI_TPC_TX_N_CHAIN; i++) + for (i = 0; i < tpc_stats->num_tx_chain; i++) *len += scnprintf(buf + *len, buf_len - *len, "tpc_value%d ", i);

diff --git a/drivers/net/wireless/ath/ath10k/wmi.c b/drivers/net/wireless/ath/ath10k/wmi.c index 3372dfa0decc..3f3fbee631c3 100644 --- a/drivers/net/wireless/ath/ath10k/wmi.c +++ b/drivers/net/wireless/ath/ath10k/wmi.c @@ -4550,16 +4550,13 @@ static void ath10k_tpc_config_disp_tables(struct ath10k *ar, }

pream_idx = 0; - for (i = 0; i < __le32_to_cpu(ev->rate_max); i++) { + for (i = 0; i < tpc_stats->rate_max; i++) { memset(tpc_value, 0, sizeof(tpc_value)); memset(buff, 0, sizeof(buff)); if (i == pream_table[pream_idx]) pream_idx++;

- for (j = 0; j < WMI_TPC_TX_N_CHAIN; j++) { - if (j >= __le32_to_cpu(ev->num_tx_chain)) - break; - + for (j = 0; j < tpc_stats->num_tx_chain; j++) { tpc[j] = ath10k_tpc_config_get_rate(ar, ev, i, j + 1, rate_code[i], type); @@ -4672,7 +4669,7 @@ void ath10k_wmi_tpc_config_get_rate_code(u8 *rate_code, u16 *pream_table,

void ath10k_wmi_event_pdev_tpc_config(struct ath10k *ar, struct sk_buff *skb) { - u32 num_tx_chain; + u32 num_tx_chain, rate_max; u8 rate_code[WMI_TPC_RATE_MAX]; u16 pream_table[WMI_TPC_PREAM_TABLE_MAX]; struct wmi_pdev_tpc_config_event *ev; @@ -4688,6 +4685,13 @@ void ath10k_wmi_event_pdev_tpc_config(struct ath10k *ar, struct sk_buff *skb) return; }

+ rate_max = __le32_to_cpu(ev->rate_max); + if (rate_max > WMI_TPC_RATE_MAX) { + ath10k_warn(ar, "number of rate is %d greater than TPC configured rate %d\n", + rate_max, WMI_TPC_RATE_MAX); + rate_max = WMI_TPC_RATE_MAX; + } + tpc_stats = kzalloc(sizeof(*tpc_stats), GFP_ATOMIC); if (!tpc_stats) return; @@ -4704,8 +4708,8 @@ void ath10k_wmi_event_pdev_tpc_config(struct ath10k *ar, struct sk_buff *skb) __le32_to_cpu(ev->twice_antenna_reduction); tpc_stats->power_limit = __le32_to_cpu(ev->power_limit); tpc_stats->twice_max_rd_power = __le32_to_cpu(ev->twice_max_rd_power); - tpc_stats->num_tx_chain = __le32_to_cpu(ev->num_tx_chain); - tpc_stats->rate_max = __le32_to_cpu(ev->rate_max); + tpc_stats->num_tx_chain = num_tx_chain; + tpc_stats->rate_max = rate_max;

ath10k_tpc_config_disp_tables(ar, ev, tpc_stats, rate_code, pream_table, @@ -4900,16 +4904,13 @@ ath10k_wmi_tpc_stats_final_disp_tables(struct ath10k *ar, }

pream_idx = 0; - for (i = 0; i < __le32_to_cpu(ev->rate_max); i++) { + for (i = 0; i < tpc_stats->rate_max; i++) { memset(tpc_value, 0, sizeof(tpc_value)); memset(buff, 0, sizeof(buff)); if (i == pream_table[pream_idx]) pream_idx++;

- for (j = 0; j < WMI_TPC_TX_N_CHAIN; j++) { - if (j >= __le32_to_cpu(ev->num_tx_chain)) - break; - + for (j = 0; j < tpc_stats->num_tx_chain; j++) { tpc[j] = ath10k_wmi_tpc_final_get_rate(ar, ev, i, j + 1, rate_code[i], type, pream_idx); @@ -4925,7 +4926,7 @@ ath10k_wmi_tpc_stats_final_disp_tables(struct ath10k *ar,

void ath10k_wmi_event_tpc_final_table(struct ath10k *ar, struct sk_buff *skb) { - u32 num_tx_chain; + u32 num_tx_chain, rate_max; u8 rate_code[WMI_TPC_FINAL_RATE_MAX]; u16 pream_table[WMI_TPC_PREAM_TABLE_MAX]; struct wmi_pdev_tpc_final_table_event *ev; @@ -4933,12 +4934,24 @@ void ath10k_wmi_event_tpc_final_table(struct ath10k *ar, struct sk_buff *skb)

ev = (struct wmi_pdev_tpc_final_table_event *)skb->data;

+ num_tx_chain = __le32_to_cpu(ev->num_tx_chain); + if (num_tx_chain > WMI_TPC_TX_N_CHAIN) { + ath10k_warn(ar, "number of tx chain is %d greater than TPC final configured tx chain %d\n", + num_tx_chain, WMI_TPC_TX_N_CHAIN); + return; + } + + rate_max = __le32_to_cpu(ev->rate_max); + if (rate_max > WMI_TPC_FINAL_RATE_MAX) { + ath10k_warn(ar, "number of rate is %d greater than TPC final configured rate %d\n", + rate_max, WMI_TPC_FINAL_RATE_MAX); + rate_max = WMI_TPC_FINAL_RATE_MAX; + } + tpc_stats = kzalloc(sizeof(*tpc_stats), GFP_ATOMIC); if (!tpc_stats) return;

- num_tx_chain = __le32_to_cpu(ev->num_tx_chain); - ath10k_wmi_tpc_config_get_rate_code(rate_code, pream_table, num_tx_chain);

@@ -4951,8 +4964,8 @@ void ath10k_wmi_event_tpc_final_table(struct ath10k *ar, struct sk_buff *skb) __le32_to_cpu(ev->twice_antenna_reduction); tpc_stats->power_limit = __le32_to_cpu(ev->power_limit); tpc_stats->twice_max_rd_power = __le32_to_cpu(ev->twice_max_rd_power); - tpc_stats->num_tx_chain = __le32_to_cpu(ev->num_tx_chain); - tpc_stats->rate_max = __le32_to_cpu(ev->rate_max); + tpc_stats->num_tx_chain = num_tx_chain; + tpc_stats->rate_max = rate_max;

ath10k_wmi_tpc_stats_final_disp_tables(ar, ev, tpc_stats, rate_code, pream_table,

From: Jia He justin.he@arm.com

[ Upstream commit 83d116c53058d505ddef051e90ab27f57015b025 ]

When we tested pmdk unit test [1] vmmalloc_fork TEST3 on arm64 guest, there will be a double page fault in __copy_from_user_inatomic of cow_user_page.

To reproduce the bug, the cmd is as follows after you deployed everything: make -C src/test/vmmalloc_fork/ TEST_TIME=60m check

Below call trace is from arm64 do_page_fault for debugging purpose: [ 110.016195] Call trace: [ 110.016826] do_page_fault+0x5a4/0x690 [ 110.017812] do_mem_abort+0x50/0xb0 [ 110.018726] el1_da+0x20/0xc4 [ 110.019492] __arch_copy_from_user+0x180/0x280 [ 110.020646] do_wp_page+0xb0/0x860 [ 110.021517] __handle_mm_fault+0x994/0x1338 [ 110.022606] handle_mm_fault+0xe8/0x180 [ 110.023584] do_page_fault+0x240/0x690 [ 110.024535] do_mem_abort+0x50/0xb0 [ 110.025423] el0_da+0x20/0x24

The pte info before __copy_from_user_inatomic is (PTE_AF is cleared): [ffff9b007000] pgd=000000023d4f8003, pud=000000023da9b003, pmd=000000023d4b3003, pte=360000298607bd3

As told by Catalin: "On arm64 without hardware Access Flag, copying from user will fail because the pte is old and cannot be marked young. So we always end up with zeroed page after fork() + CoW for pfn mappings. we don't always have a hardware-managed access flag on arm64."

This patch fixes it by calling pte_mkyoung. Also, the parameter is changed because vmf should be passed to cow_user_page()

Add a WARN_ON_ONCE when __copy_from_user_inatomic() returns error in case there can be some obscure use-case (by Kirill).

[1] https://github.com/pmem/pmdk/tree/master/src/test/vmmalloc_fork

Signed-off-by: Jia He justin.he@arm.com Reported-by: Yibo Cai Yibo.Cai@arm.com Reviewed-by: Catalin Marinas catalin.marinas@arm.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Signed-off-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- mm/memory.c | 104 ++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 89 insertions(+), 15 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c index 852d2ffcc08d..6a3d5eebc951 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -117,6 +117,18 @@ int randomize_va_space __read_mostly = 2; #endif

+#ifndef arch_faults_on_old_pte +static inline bool arch_faults_on_old_pte(void) +{ + /* + * Those arches which don't have hw access flag feature need to + * implement their own helper. By default, "true" means pagefault + * will be hit on old pte. + */ + return true; +} +#endif + static int __init disable_randmaps(char *s) { randomize_va_space = 0; @@ -2089,32 +2101,82 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, return same; }

-static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma) +static inline bool cow_user_page(struct page *dst, struct page *src, + struct vm_fault *vmf) { + bool ret; + void *kaddr; + void __user *uaddr; + bool force_mkyoung; + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *mm = vma->vm_mm; + unsigned long addr = vmf->address; + debug_dma_assert_idle(src);

+ if (likely(src)) { + copy_user_highpage(dst, src, addr, vma); + return true; + } + /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ - if (unlikely(!src)) { - void *kaddr = kmap_atomic(dst); - void __user *uaddr = (void __user *)(va & PAGE_MASK); + kaddr = kmap_atomic(dst); + uaddr = (void __user *)(addr & PAGE_MASK); + + /* + * On architectures with software "accessed" bits, we would + * take a double page fault, so mark it accessed here. + */ + force_mkyoung = arch_faults_on_old_pte() && !pte_young(vmf->orig_pte); + if (force_mkyoung) { + pte_t entry; + + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { + /* + * Other thread has already handled the fault + * and we don't need to do anything. If it's + * not the case, the fault will be triggered + * again on the same address. + */ + ret = false; + goto pte_unlock; + }

+ entry = pte_mkyoung(vmf->orig_pte); + if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) + update_mmu_cache(vma, addr, vmf->pte); + } + + /* + * This really shouldn't fail, because the page is there + * in the page tables. But it might just be unreadable, + * in which case we just give up and fill the result with + * zeroes. + */ + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { /* - * This really shouldn't fail, because the page is there - * in the page tables. But it might just be unreadable, - * in which case we just give up and fill the result with - * zeroes. + * Give a warn in case there can be some obscure + * use-case */ - if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) - clear_page(kaddr); - kunmap_atomic(kaddr); - flush_dcache_page(dst); - } else - copy_user_highpage(dst, src, va, vma); + WARN_ON_ONCE(1); + clear_page(kaddr); + } + + ret = true; + +pte_unlock: + if (force_mkyoung) + pte_unmap_unlock(vmf->pte, vmf->ptl); + kunmap_atomic(kaddr); + flush_dcache_page(dst); + + return ret; }

static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) @@ -2268,7 +2330,19 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) vmf->address); if (!new_page) goto oom; - cow_user_page(new_page, old_page, vmf->address, vma); + + if (!cow_user_page(new_page, old_page, vmf)) { + /* + * COW failed, if the fault was solved by other, + * it's fine. If not, userspace would re-fault on + * the same address and we will handle the fault + * from the second attempt. + */ + put_page(new_page); + if (old_page) + put_page(old_page); + return 0; + } }

if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false))

From: Fuqian Huang huangfq.daxian@gmail.com

[ Upstream commit 7cf78b6b12fd5550545e4b73b35dca18bd46b44c ]

When the option is RTC_PLL_GET, pll will be copied to userland via copy_to_user. pll is initialized using mach_get_rtc_pll indirect call and mach_get_rtc_pll is only assigned with function q40_get_rtc_pll in arch/m68k/q40/config.c. In function q40_get_rtc_pll, the field pll_ctrl is not initialized. This will leak uninitialized stack content to userland. Fix this by zeroing the uninitialized field.

Signed-off-by: Fuqian Huang huangfq.daxian@gmail.com Link: https://lore.kernel.org/r/20190927121544.7650-1-huangfq.daxian@gmail.com Signed-off-by: Geert Uytterhoeven geert@linux-m68k.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- arch/m68k/q40/config.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/arch/m68k/q40/config.c b/arch/m68k/q40/config.c index 96810d91da2b..4a25ce6a1823 100644 --- a/arch/m68k/q40/config.c +++ b/arch/m68k/q40/config.c @@ -273,6 +273,7 @@ static int q40_get_rtc_pll(struct rtc_pll_info *pll) { int tmp = Q40_RTC_CTRL;

+ pll->pll_ctrl = 0; pll->pll_value = tmp & Q40_RTC_PLL_MASK; if (tmp & Q40_RTC_PLL_SIGN) pll->pll_value = -pll->pll_value;

From: Russell King rmk+kernel@armlinux.org.uk

[ Upstream commit 175fc928198236037174e5c5c066fe3c4691903e ]

Propagate the error code from request_irq(), rather than returning -EBUSY.

Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Link: https://lore.kernel.org/r/E1iNIqh-0000tW-EZ@rmk-PC.armlinux.org.uk Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- sound/soc/kirkwood/kirkwood-dma.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/kirkwood/kirkwood-dma.c b/sound/soc/kirkwood/kirkwood-dma.c index c6a58520d377..255cc45905b8 100644 --- a/sound/soc/kirkwood/kirkwood-dma.c +++ b/sound/soc/kirkwood/kirkwood-dma.c @@ -136,7 +136,7 @@ static int kirkwood_dma_open(struct snd_pcm_substream *substream) err = request_irq(priv->irq, kirkwood_dma_irq, IRQF_SHARED, "kirkwood-i2s", priv); if (err) - return -EBUSY; + return err;

/* * Enable Error interrupts. We're only ack'ing them but

From: Mikulas Patocka mpatocka@redhat.com

commit a1cd6c2ae47ee10ff21e62475685d5b399e2ed4a upstream.

If we copy less than 8 bytes and if the destination crosses a cache line, __copy_user_flushcache would invalidate only the first cache line.

This patch makes it invalidate the second cache line as well.

Fixes: 0aed55af88345b ("x86, uaccess: introduce copy_from_iter_flushcache for pmem / cache-bypass operations") Signed-off-by: Mikulas Patocka mpatocka@redhat.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Reviewed-by: Dan Williams dan.j.wiilliams@intel.com Cc: Jan Kara jack@suse.cz Cc: Jeff Moyer jmoyer@redhat.com Cc: Ingo Molnar mingo@redhat.com Cc: Christoph Hellwig hch@lst.de Cc: Toshi Kani toshi.kani@hpe.com Cc: "H. Peter Anvin" hpa@zytor.com Cc: Al Viro viro@zeniv.linux.org.uk Cc: Thomas Gleixner tglx@linutronix.de Cc: Matthew Wilcox mawilcox@microsoft.com Cc: Ross Zwisler ross.zwisler@linux.intel.com Cc: Ingo Molnar mingo@elte.hu Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/alpine.LRH.2.02.2009161451140.21915@file01.intrane... Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- arch/x86/lib/usercopy_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c index 8e35df5454fc..740342715ea6 100644 --- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -139,7 +139,7 @@ long __copy_user_flushcache(void *dst, const void __user *src, unsigned size) */ if (size < 8) { if (!IS_ALIGNED(dest, 4) || size != 4) - clean_cache_range(dst, 1); + clean_cache_range(dst, size); } else { if (!IS_ALIGNED(dest, 8)) { dest = ALIGN(dest, boot_cpu_data.x86_clflush_size);

From: Joakim Tjernlund joakim.tjernlund@infinera.com

commit 315c7ad7a701baba28c628c4c5426b3d9617ceed upstream.

Needs the same delay as H650e

Signed-off-by: Joakim Tjernlund joakim.tjernlund@infinera.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200910085328.19188-1-joakim.tjernlund@infinera.c... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- sound/usb/quirks.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c index 8d9117312e30..e6dea1c7112b 100644 --- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1338,12 +1338,13 @@ void snd_usb_ctl_msg_quirk(struct usb_device *dev, unsigned int pipe, && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS) msleep(20);

- /* Zoom R16/24, Logitech H650e, Jabra 550a, Kingston HyperX needs a tiny - * delay here, otherwise requests like get/set frequency return as - * failed despite actually succeeding. + /* Zoom R16/24, Logitech H650e/H570e, Jabra 550a, Kingston HyperX + * needs a tiny delay here, otherwise requests like get/set + * frequency return as failed despite actually succeeding. */ if ((chip->usb_id == USB_ID(0x1686, 0x00dd) || chip->usb_id == USB_ID(0x046d, 0x0a46) || + chip->usb_id == USB_ID(0x046d, 0x0a56) || chip->usb_id == USB_ID(0x0b0e, 0x0349) || chip->usb_id == USB_ID(0x0951, 0x16ad)) && (requesttype & USB_TYPE_MASK) == USB_TYPE_CLASS)

From: Kai-Heng Feng kai.heng.feng@canonical.com

commit f73bbf639b32acb6b409e188fdde5644b301978f upstream.

On Lenovo P520, the front panel headset LED isn't lit up right now.

Realtek states that the LED needs to be enabled by ALC233's GPIO2, so let's do it accordingly to light the LED up.

Signed-off-by: Kai-Heng Feng kai.heng.feng@canonical.com Acked-by: Hui Wang hui.wang@canonical.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20200914070231.13192-1-kai.heng.feng@canonical.com Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- sound/pci/hda/patch_realtek.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 4d923d6633c1..24bc9e446047 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5616,6 +5616,7 @@ static void alc_fixup_thinkpad_acpi(struct hda_codec *codec, #include "hp_x360_helper.c"

enum { + ALC269_FIXUP_GPIO2, ALC269_FIXUP_SONY_VAIO, ALC275_FIXUP_SONY_VAIO_GPIO2, ALC269_FIXUP_DELL_M101Z, @@ -5768,6 +5769,10 @@ enum { };

static const struct hda_fixup alc269_fixups[] = { + [ALC269_FIXUP_GPIO2] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_gpio2, + }, [ALC269_FIXUP_SONY_VAIO] = { .type = HDA_FIXUP_PINCTLS, .v.pins = (const struct hda_pintbl[]) { @@ -6563,6 +6568,8 @@ static const struct hda_fixup alc269_fixups[] = { [ALC233_FIXUP_LENOVO_MULTI_CODECS] = { .type = HDA_FIXUP_FUNC, .v.func = alc233_alc662_fixup_lenovo_dual_codecs, + .chained = true, + .chain_id = ALC269_FIXUP_GPIO2 }, [ALC233_FIXUP_ACER_HEADSET_MIC] = { .type = HDA_FIXUP_VERBS,

From: Oleh Kravchenko oleg@kaa.org.ua

[ Upstream commit 7c6082b903ac28dc3f383fba57c6f9e7e2594178 ]

Error was detected by PVS-Studio: V512 A call of the 'sprintf' function will lead to overflow of the buffer 'led_data->led_cdev_name'.

Acked-by: Jacek Anaszewski jacek.anaszewski@gmail.com Acked-by: Pavel Machek pavel@ucw.cz Signed-off-by: Oleh Kravchenko oleg@kaa.org.ua Signed-off-by: Pavel Machek pavel@ucw.cz Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/leds/leds-mlxreg.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/leds/leds-mlxreg.c b/drivers/leds/leds-mlxreg.c index 1ee48cb21df9..022e973dc7c3 100644 --- a/drivers/leds/leds-mlxreg.c +++ b/drivers/leds/leds-mlxreg.c @@ -209,8 +209,8 @@ static int mlxreg_led_config(struct mlxreg_led_priv_data *priv) brightness = LED_OFF; led_data->base_color = MLXREG_LED_GREEN_SOLID; } - sprintf(led_data->led_cdev_name, "%s:%s", "mlxreg", - data->label); + snprintf(led_data->led_cdev_name, sizeof(led_data->led_cdev_name), + "mlxreg:%s", data->label); led_cdev->name = led_data->led_cdev_name; led_cdev->brightness = brightness; led_cdev->max_brightness = LED_ON;

From: Pan Bian bianpan2016@163.com

[ Upstream commit ec990306f77fd4c58c3b27cc3b3c53032d6e6670 ]

The memory chunk io_req is released by mempool_free. Accessing io_req->start_time will result in a use after free bug. The variable start_time is a backup of the timestamp. So, use start_time here to avoid use after free.

Link: https://lore.kernel.org/r/1572881182-37664-1-git-send-email-bianpan2016@163.... Signed-off-by: Pan Bian bianpan2016@163.com Reviewed-by: Satish Kharat satishkh@cisco.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/scsi/fnic/fnic_scsi.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/scsi/fnic/fnic_scsi.c b/drivers/scsi/fnic/fnic_scsi.c index 73ffc16ec022..b521fc7650cb 100644 --- a/drivers/scsi/fnic/fnic_scsi.c +++ b/drivers/scsi/fnic/fnic_scsi.c @@ -1034,7 +1034,8 @@ static void fnic_fcpio_icmnd_cmpl_handler(struct fnic *fnic, atomic64_inc(&fnic_stats->io_stats.io_completions);

- io_duration_time = jiffies_to_msecs(jiffies) - jiffies_to_msecs(io_req->start_time); + io_duration_time = jiffies_to_msecs(jiffies) - + jiffies_to_msecs(start_time);

if(io_duration_time <= 10) atomic64_inc(&fnic_stats->io_stats.io_btw_0_to_10_msec);

From: Eric Dumazet edumazet@google.com

[ Upstream commit 9ed498c6280a2f2b51d02df96df53037272ede49 ]

sk->sk_backlog.tail might be read without holding the socket spinlock, we need to add proper READ_ONCE()/WRITE_ONCE() to silence the warnings.

KCSAN reported :

BUG: KCSAN: data-race in tcp_add_backlog / tcp_recvmsg

write to 0xffff8881265109f8 of 8 bytes by interrupt on cpu 1: __sk_add_backlog include/net/sock.h:907 [inline] sk_add_backlog include/net/sock.h:938 [inline] tcp_add_backlog+0x476/0xce0 net/ipv4/tcp_ipv4.c:1759 tcp_v4_rcv+0x1a70/0x1bd0 net/ipv4/tcp_ipv4.c:1947 ip_protocol_deliver_rcu+0x4d/0x420 net/ipv4/ip_input.c:204 ip_local_deliver_finish+0x110/0x140 net/ipv4/ip_input.c:231 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_local_deliver+0x133/0x210 net/ipv4/ip_input.c:252 dst_input include/net/dst.h:442 [inline] ip_rcv_finish+0x121/0x160 net/ipv4/ip_input.c:413 NF_HOOK include/linux/netfilter.h:305 [inline] NF_HOOK include/linux/netfilter.h:299 [inline] ip_rcv+0x18f/0x1a0 net/ipv4/ip_input.c:523 __netif_receive_skb_one_core+0xa7/0xe0 net/core/dev.c:4929 __netif_receive_skb+0x37/0xf0 net/core/dev.c:5043 netif_receive_skb_internal+0x59/0x190 net/core/dev.c:5133 napi_skb_finish net/core/dev.c:5596 [inline] napi_gro_receive+0x28f/0x330 net/core/dev.c:5629 receive_buf+0x284/0x30b0 drivers/net/virtio_net.c:1061 virtnet_receive drivers/net/virtio_net.c:1323 [inline] virtnet_poll+0x436/0x7d0 drivers/net/virtio_net.c:1428 napi_poll net/core/dev.c:6311 [inline] net_rx_action+0x3ae/0xa90 net/core/dev.c:6379 __do_softirq+0x115/0x33f kernel/softirq.c:292 invoke_softirq kernel/softirq.c:373 [inline] irq_exit+0xbb/0xe0 kernel/softirq.c:413 exiting_irq arch/x86/include/asm/apic.h:536 [inline] do_IRQ+0xa6/0x180 arch/x86/kernel/irq.c:263 ret_from_intr+0x0/0x19 native_safe_halt+0xe/0x10 arch/x86/kernel/paravirt.c:71 arch_cpu_idle+0x1f/0x30 arch/x86/kernel/process.c:571 default_idle_call+0x1e/0x40 kernel/sched/idle.c:94 cpuidle_idle_call kernel/sched/idle.c:154 [inline] do_idle+0x1af/0x280 kernel/sched/idle.c:263 cpu_startup_entry+0x1b/0x20 kernel/sched/idle.c:355 start_secondary+0x208/0x260 arch/x86/kernel/smpboot.c:264 secondary_startup_64+0xa4/0xb0 arch/x86/kernel/head_64.S:241

read to 0xffff8881265109f8 of 8 bytes by task 8057 on cpu 0: tcp_recvmsg+0x46e/0x1b40 net/ipv4/tcp.c:2050 inet_recvmsg+0xbb/0x250 net/ipv4/af_inet.c:838 sock_recvmsg_nosec net/socket.c:871 [inline] sock_recvmsg net/socket.c:889 [inline] sock_recvmsg+0x92/0xb0 net/socket.c:885 sock_read_iter+0x15f/0x1e0 net/socket.c:967 call_read_iter include/linux/fs.h:1889 [inline] new_sync_read+0x389/0x4f0 fs/read_write.c:414 __vfs_read+0xb1/0xc0 fs/read_write.c:427 vfs_read fs/read_write.c:461 [inline] vfs_read+0x143/0x2c0 fs/read_write.c:446 ksys_read+0xd5/0x1b0 fs/read_write.c:587 __do_sys_read fs/read_write.c:597 [inline] __se_sys_read fs/read_write.c:595 [inline] __x64_sys_read+0x4c/0x60 fs/read_write.c:595 do_syscall_64+0xcc/0x370 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x44/0xa9

Reported by Kernel Concurrency Sanitizer on: CPU: 0 PID: 8057 Comm: syz-fuzzer Not tainted 5.4.0-rc6+ #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011

Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/crypto/chelsio/chtls/chtls_io.c | 10 +++++----- include/net/sock.h | 4 ++-- net/ipv4/tcp.c | 2 +- net/llc/af_llc.c | 2 +- 4 files changed, 9 insertions(+), 9 deletions(-)

diff --git a/drivers/crypto/chelsio/chtls/chtls_io.c b/drivers/crypto/chelsio/chtls/chtls_io.c index a2ba85b4371d..3e67558dbded 100644 --- a/drivers/crypto/chelsio/chtls/chtls_io.c +++ b/drivers/crypto/chelsio/chtls/chtls_io.c @@ -1445,7 +1445,7 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, csk->wr_max_credits)) sk->sk_write_space(sk);

- if (copied >= target && !sk->sk_backlog.tail) + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break;

if (copied) { @@ -1478,7 +1478,7 @@ static int chtls_pt_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, break; } } - if (sk->sk_backlog.tail) { + if (READ_ONCE(sk->sk_backlog.tail)) { release_sock(sk); lock_sock(sk); chtls_cleanup_rbuf(sk, copied); @@ -1623,7 +1623,7 @@ static int peekmsg(struct sock *sk, struct msghdr *msg, break; }

- if (sk->sk_backlog.tail) { + if (READ_ONCE(sk->sk_backlog.tail)) { /* Do not sleep, just process backlog. */ release_sock(sk); lock_sock(sk); @@ -1755,7 +1755,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, csk->wr_max_credits)) sk->sk_write_space(sk);

- if (copied >= target && !sk->sk_backlog.tail) + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break;

if (copied) { @@ -1786,7 +1786,7 @@ int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } }

- if (sk->sk_backlog.tail) { + if (READ_ONCE(sk->sk_backlog.tail)) { release_sock(sk); lock_sock(sk); chtls_cleanup_rbuf(sk, copied); diff --git a/include/net/sock.h b/include/net/sock.h index b5fb4d367406..0a26b42a7b2f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -918,11 +918,11 @@ static inline void __sk_add_backlog(struct sock *sk, struct sk_buff *skb) skb_dst_force(skb);

if (!sk->sk_backlog.tail) - sk->sk_backlog.head = skb; + WRITE_ONCE(sk->sk_backlog.head, skb); else sk->sk_backlog.tail->next = skb;

- sk->sk_backlog.tail = skb; + WRITE_ONCE(sk->sk_backlog.tail, skb); skb->next = NULL; }

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 616ff2970f4f..4ce3397e6fcf 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2038,7 +2038,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,

/* Well, if we have backlog, try to process it now yet. */

- if (copied >= target && !sk->sk_backlog.tail) + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break;

if (copied) { diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 5abb7f9b7ee5..fa0f3c1543ba 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -784,7 +784,7 @@ static int llc_ui_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, } /* Well, if we have backlog, try to process it now yet. */

- if (copied >= target && !sk->sk_backlog.tail) + if (copied >= target && !READ_ONCE(sk->sk_backlog.tail)) break;

if (copied) {

From: Alex Deucher alexander.deucher@amd.com

[ Upstream commit 53dbc27ad5a93932ff1892a8e4ef266827d74a0f ]

When a custom powerplay table is provided, we need to update the OD VDDC flag to avoid AVFS being enabled when it shouldn't be.

Bug: https://bugzilla.kernel.org/show_bug.cgi?id=205393 Reviewed-by: Evan Quan evan.quan@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c | 7 +++++++ 1 file changed, 7 insertions(+)

diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c index ce459ea4ec3a..da9e6923fa65 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega10_hwmgr.c @@ -3591,6 +3591,13 @@ static int vega10_set_power_state_tasks(struct pp_hwmgr *hwmgr, PP_ASSERT_WITH_CODE(!result, "Failed to upload PPtable!", return result);

+ /* + * If a custom pp table is loaded, set DPMTABLE_OD_UPDATE_VDDC flag. + * That effectively disables AVFS feature. + */ + if(hwmgr->hardcode_pp_table != NULL) + data->need_update_dpm_table |= DPMTABLE_OD_UPDATE_VDDC; + vega10_update_avfs(hwmgr);

data->need_update_dpm_table &= DPMTABLE_OD_UPDATE_VDDC;

From: Lee Jones lee.jones@linaro.org

[ Upstream commit b195e101580db390f50b0d587b7f66f241d2bc88 ]

If a child device calls mfd_cell_{en,dis}able() without an appropriate call-back being set, we are likely to encounter a panic. Avoid this by adding suitable checking.

Signed-off-by: Lee Jones lee.jones@linaro.org Reviewed-by: Daniel Thompson daniel.thompson@linaro.org Reviewed-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/mfd/mfd-core.c | 10 ++++++++++ 1 file changed, 10 insertions(+)

diff --git a/drivers/mfd/mfd-core.c b/drivers/mfd/mfd-core.c index 182973df1aed..77c965c6a65f 100644 --- a/drivers/mfd/mfd-core.c +++ b/drivers/mfd/mfd-core.c @@ -32,6 +32,11 @@ int mfd_cell_enable(struct platform_device *pdev) const struct mfd_cell *cell = mfd_get_cell(pdev); int err = 0;

+ if (!cell->enable) { + dev_dbg(&pdev->dev, "No .enable() call-back registered\n"); + return 0; + } + /* only call enable hook if the cell wasn't previously enabled */ if (atomic_inc_return(cell->usage_count) == 1) err = cell->enable(pdev); @@ -49,6 +54,11 @@ int mfd_cell_disable(struct platform_device *pdev) const struct mfd_cell *cell = mfd_get_cell(pdev); int err = 0;

+ if (!cell->disable) { + dev_dbg(&pdev->dev, "No .disable() call-back registered\n"); + return 0; + } + /* only disable if no other clients are using it */ if (atomic_dec_return(cell->usage_count) == 0) err = cell->disable(pdev);

From: Ivan Lazeev ivan.lazeev@gmail.com

[ Upstream commit 3ef193822b25e9ee629974f66dc1ff65167f770c ]

Bug link: https://bugzilla.kernel.org/show_bug.cgi?id=195657

cmd/rsp buffers are expected to be in the same ACPI region. For Zen+ CPUs BIOS's might report two different regions, some of them also report region sizes inconsistent with values from TPM registers.

Memory configuration on ASRock x470 ITX:

db0a0000-dc59efff : Reserved dc57e000-dc57efff : MSFT0101:00 dc582000-dc582fff : MSFT0101:00

Work around the issue by storing ACPI regions declared for the device in a fixed array and adding an array for pointers to corresponding possibly allocated resources in crb_map_io function. This data was previously held for a single resource in struct crb_priv (iobase field) and local variable io_res in crb_map_io function. ACPI resources array is used to find index of corresponding region for each buffer and make the buffer size consistent with region's length. Array of pointers to allocated resources is used to map the region at most once.

Signed-off-by: Ivan Lazeev ivan.lazeev@gmail.com Tested-by: Jerry Snitselaar jsnitsel@redhat.com Tested-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Reviewed-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Signed-off-by: Jarkko Sakkinen jarkko.sakkinen@linux.intel.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/char/tpm/tpm_crb.c | 123 +++++++++++++++++++++++++++---------- 1 file changed, 90 insertions(+), 33 deletions(-)

diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index 763fc7e6c005..20f27100708b 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -26,6 +26,7 @@ #include "tpm.h"

#define ACPI_SIG_TPM2 "TPM2" +#define TPM_CRB_MAX_RESOURCES 3

static const guid_t crb_acpi_start_guid = GUID_INIT(0x6BBF6CAB, 0x5463, 0x4714, @@ -95,7 +96,6 @@ enum crb_status { struct crb_priv { u32 sm; const char *hid; - void __iomem *iobase; struct crb_regs_head __iomem *regs_h; struct crb_regs_tail __iomem *regs_t; u8 __iomem *cmd; @@ -438,21 +438,27 @@ static const struct tpm_class_ops tpm_crb = {

static int crb_check_resource(struct acpi_resource *ares, void *data) { - struct resource *io_res = data; + struct resource *iores_array = data; struct resource_win win; struct resource *res = &(win.res); + int i;

if (acpi_dev_resource_memory(ares, res) || acpi_dev_resource_address_space(ares, &win)) { - *io_res = *res; - io_res->name = NULL; + for (i = 0; i < TPM_CRB_MAX_RESOURCES + 1; ++i) { + if (resource_type(iores_array + i) != IORESOURCE_MEM) { + iores_array[i] = *res; + iores_array[i].name = NULL; + break; + } + } }

return 1; }

-static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv, - struct resource *io_res, u64 start, u32 size) +static void __iomem *crb_map_res(struct device *dev, struct resource *iores, + void __iomem **iobase_ptr, u64 start, u32 size) { struct resource new_res = { .start = start, @@ -464,10 +470,16 @@ static void __iomem *crb_map_res(struct device *dev, struct crb_priv *priv, if (start != new_res.start) return (void __iomem *) ERR_PTR(-EINVAL);

- if (!resource_contains(io_res, &new_res)) + if (!iores) return devm_ioremap_resource(dev, &new_res);

- return priv->iobase + (new_res.start - io_res->start); + if (!*iobase_ptr) { + *iobase_ptr = devm_ioremap_resource(dev, iores); + if (IS_ERR(*iobase_ptr)) + return *iobase_ptr; + } + + return *iobase_ptr + (new_res.start - iores->start); }

/* @@ -494,9 +506,13 @@ static u64 crb_fixup_cmd_size(struct device *dev, struct resource *io_res, static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, struct acpi_table_tpm2 *buf) { - struct list_head resources; - struct resource io_res; + struct list_head acpi_resource_list; + struct resource iores_array[TPM_CRB_MAX_RESOURCES + 1] = { {0} }; + void __iomem *iobase_array[TPM_CRB_MAX_RESOURCES] = {NULL}; struct device *dev = &device->dev; + struct resource *iores; + void __iomem **iobase_ptr; + int i; u32 pa_high, pa_low; u64 cmd_pa; u32 cmd_size; @@ -505,21 +521,41 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, u32 rsp_size; int ret;

- INIT_LIST_HEAD(&resources); - ret = acpi_dev_get_resources(device, &resources, crb_check_resource, - &io_res); + INIT_LIST_HEAD(&acpi_resource_list); + ret = acpi_dev_get_resources(device, &acpi_resource_list, + crb_check_resource, iores_array); if (ret < 0) return ret; - acpi_dev_free_resource_list(&resources); + acpi_dev_free_resource_list(&acpi_resource_list);

- if (resource_type(&io_res) != IORESOURCE_MEM) { + if (resource_type(iores_array) != IORESOURCE_MEM) { dev_err(dev, FW_BUG "TPM2 ACPI table does not define a memory resource\n"); return -EINVAL; + } else if (resource_type(iores_array + TPM_CRB_MAX_RESOURCES) == + IORESOURCE_MEM) { + dev_warn(dev, "TPM2 ACPI table defines too many memory resources\n"); + memset(iores_array + TPM_CRB_MAX_RESOURCES, + 0, sizeof(*iores_array)); + iores_array[TPM_CRB_MAX_RESOURCES].flags = 0; }

- priv->iobase = devm_ioremap_resource(dev, &io_res); - if (IS_ERR(priv->iobase)) - return PTR_ERR(priv->iobase); + iores = NULL; + iobase_ptr = NULL; + for (i = 0; resource_type(iores_array + i) == IORESOURCE_MEM; ++i) { + if (buf->control_address >= iores_array[i].start && + buf->control_address + sizeof(struct crb_regs_tail) - 1 <= + iores_array[i].end) { + iores = iores_array + i; + iobase_ptr = iobase_array + i; + break; + } + } + + priv->regs_t = crb_map_res(dev, iores, iobase_ptr, buf->control_address, + sizeof(struct crb_regs_tail)); + + if (IS_ERR(priv->regs_t)) + return PTR_ERR(priv->regs_t);

/* The ACPI IO region starts at the head area and continues to include * the control area, as one nice sane region except for some older @@ -527,9 +563,10 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, */ if ((priv->sm == ACPI_TPM2_COMMAND_BUFFER) || (priv->sm == ACPI_TPM2_MEMORY_MAPPED)) { - if (buf->control_address == io_res.start + + if (iores && + buf->control_address == iores->start + sizeof(*priv->regs_h)) - priv->regs_h = priv->iobase; + priv->regs_h = *iobase_ptr; else dev_warn(dev, FW_BUG "Bad ACPI memory layout"); } @@ -538,13 +575,6 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, if (ret) return ret;

- priv->regs_t = crb_map_res(dev, priv, &io_res, buf->control_address, - sizeof(struct crb_regs_tail)); - if (IS_ERR(priv->regs_t)) { - ret = PTR_ERR(priv->regs_t); - goto out_relinquish_locality; - } - /* * PTT HW bug w/a: wake up the device to access * possibly not retained registers. @@ -556,13 +586,26 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, pa_high = ioread32(&priv->regs_t->ctrl_cmd_pa_high); pa_low = ioread32(&priv->regs_t->ctrl_cmd_pa_low); cmd_pa = ((u64)pa_high << 32) | pa_low; - cmd_size = crb_fixup_cmd_size(dev, &io_res, cmd_pa, - ioread32(&priv->regs_t->ctrl_cmd_size)); + cmd_size = ioread32(&priv->regs_t->ctrl_cmd_size); + + iores = NULL; + iobase_ptr = NULL; + for (i = 0; iores_array[i].end; ++i) { + if (cmd_pa >= iores_array[i].start && + cmd_pa <= iores_array[i].end) { + iores = iores_array + i; + iobase_ptr = iobase_array + i; + break; + } + } + + if (iores) + cmd_size = crb_fixup_cmd_size(dev, iores, cmd_pa, cmd_size);

dev_dbg(dev, "cmd_hi = %X cmd_low = %X cmd_size %X\n", pa_high, pa_low, cmd_size);

- priv->cmd = crb_map_res(dev, priv, &io_res, cmd_pa, cmd_size); + priv->cmd = crb_map_res(dev, iores, iobase_ptr, cmd_pa, cmd_size); if (IS_ERR(priv->cmd)) { ret = PTR_ERR(priv->cmd); goto out; @@ -570,11 +613,25 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv,

memcpy_fromio(&__rsp_pa, &priv->regs_t->ctrl_rsp_pa, 8); rsp_pa = le64_to_cpu(__rsp_pa); - rsp_size = crb_fixup_cmd_size(dev, &io_res, rsp_pa, - ioread32(&priv->regs_t->ctrl_rsp_size)); + rsp_size = ioread32(&priv->regs_t->ctrl_rsp_size); + + iores = NULL; + iobase_ptr = NULL; + for (i = 0; resource_type(iores_array + i) == IORESOURCE_MEM; ++i) { + if (rsp_pa >= iores_array[i].start && + rsp_pa <= iores_array[i].end) { + iores = iores_array + i; + iobase_ptr = iobase_array + i; + break; + } + } + + if (iores) + rsp_size = crb_fixup_cmd_size(dev, iores, rsp_pa, rsp_size);

if (cmd_pa != rsp_pa) { - priv->rsp = crb_map_res(dev, priv, &io_res, rsp_pa, rsp_size); + priv->rsp = crb_map_res(dev, iores, iobase_ptr, + rsp_pa, rsp_size); ret = PTR_ERR_OR_ZERO(priv->rsp); goto out; }

From: Satendra Singh Thakur sst2005@gmail.com

[ Upstream commit 1ff95243257fad07290dcbc5f7a6ad79d6e703e2 ]

When devm_request_irq fails, currently, the function dma_async_device_unregister gets called. This doesn't free the resources allocated by of_dma_controller_register. Therefore, we have called of_dma_controller_free for this purpose.

Signed-off-by: Satendra Singh Thakur sst2005@gmail.com Link: https://lore.kernel.org/r/20191109113523.6067-1-sst2005@gmail.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/dma/mediatek/mtk-hsdma.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/dma/mediatek/mtk-hsdma.c b/drivers/dma/mediatek/mtk-hsdma.c index b7ec56ae02a6..fca232b1d4a6 100644 --- a/drivers/dma/mediatek/mtk-hsdma.c +++ b/drivers/dma/mediatek/mtk-hsdma.c @@ -997,7 +997,7 @@ static int mtk_hsdma_probe(struct platform_device *pdev) if (err) { dev_err(&pdev->dev, "request_irq failed with err %d\n", err); - goto err_unregister; + goto err_free; }

platform_set_drvdata(pdev, hsdma); @@ -1006,6 +1006,8 @@ static int mtk_hsdma_probe(struct platform_device *pdev)

return 0;

+err_free: + of_dma_controller_free(pdev->dev.of_node); err_unregister: dma_async_device_unregister(dd);

From: Pan Bian bianpan2016@163.com

[ Upstream commit da046d5f895fca18d63b15ac8faebd5bf784e23a ]

Release variable dst after logging dst->error to avoid possible use after free.

Link: https://lore.kernel.org/r/1573022651-37171-1-git-send-email-bianpan2016@163.... Signed-off-by: Pan Bian bianpan2016@163.com Reviewed-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/infiniband/hw/i40iw/i40iw_cm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/i40iw/i40iw_cm.c b/drivers/infiniband/hw/i40iw/i40iw_cm.c index 4321b9e3dbb4..0273d0404e74 100644 --- a/drivers/infiniband/hw/i40iw/i40iw_cm.c +++ b/drivers/infiniband/hw/i40iw/i40iw_cm.c @@ -2071,9 +2071,9 @@ static int i40iw_addr_resolve_neigh_ipv6(struct i40iw_device *iwdev, dst = i40iw_get_dst_ipv6(&src_addr, &dst_addr); if (!dst || dst->error) { if (dst) { - dst_release(dst); i40iw_pr_err("ip6_route_output returned dst->error = %d\n", dst->error); + dst_release(dst); } return rc; }

From: Brian Foster bfoster@redhat.com

[ Upstream commit 2a2b5932db67586bacc560cc065d62faece5b996 ]

The leaf format xattr addition helper xfs_attr3_leaf_add_work() adjusts the block freemap in a couple places. The first update drops the size of the freemap that the caller had already selected to place the xattr name/value data. Before the function returns, it also checks whether the entries array has encroached on a freemap range by virtue of the new entry addition. This is necessary because the entries array grows from the start of the block (but end of the block header) towards the end of the block while the name/value data grows from the end of the block in the opposite direction. If the associated freemap is already empty, however, size is zero and the subtraction underflows the field and causes corruption.

This is reproduced rarely by generic/070. The observed behavior is that a smaller sized freemap is aligned to the end of the entries list, several subsequent xattr additions land in larger freemaps and the entries list expands into the smaller freemap until it is fully consumed and then underflows. Note that it is not otherwise a corruption for the entries array to consume an empty freemap because the nameval list (i.e. the firstused pointer in the xattr header) starts beyond the end of the corrupted freemap.

Update the freemap size modification to account for the fact that the freemap entry can be empty and thus stale.

Signed-off-by: Brian Foster bfoster@redhat.com Reviewed-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/xfs/libxfs/xfs_attr_leaf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c index 39df2c5425fa..880fadb19fc0 100644 --- a/fs/xfs/libxfs/xfs_attr_leaf.c +++ b/fs/xfs/libxfs/xfs_attr_leaf.c @@ -1440,7 +1440,9 @@ xfs_attr3_leaf_add_work( for (i = 0; i < XFS_ATTR_LEAF_MAPSIZE; i++) { if (ichdr->freemap[i].base == tmp) { ichdr->freemap[i].base += sizeof(xfs_attr_leaf_entry_t); - ichdr->freemap[i].size -= sizeof(xfs_attr_leaf_entry_t); + ichdr->freemap[i].size -= + min_t(uint16_t, ichdr->freemap[i].size, + sizeof(xfs_attr_leaf_entry_t)); } } ichdr->usedbytes += xfs_attr_leaf_entsize(leaf, args->index);

From: Sascha Hauer s.hauer@pengutronix.de

[ Upstream commit f9c34bb529975fe9f85b870a80c53a83a3c5a182 ]

When a new fastmap is about to be written UBI must make sure it has a free block for a fastmap anchor available. For this ubi_update_fastmap() calls ubi_ensure_anchor_pebs(). This stopped working with 2e8f08deabbc ("ubi: Fix races around ubi_refill_pools()"), with this commit the wear leveling code is blocked and can no longer produce free PEBs. UBI then more often than not falls back to write the new fastmap anchor to the same block it was already on which means the same erase block gets erased during each fastmap write and wears out quite fast.

As the locking prevents us from producing the anchor PEB when we actually need it, this patch changes the strategy for creating the anchor PEB. We no longer create it on demand right before we want to write a fastmap, but instead we create an anchor PEB right after we have written a fastmap. This gives us enough time to produce a new anchor PEB before it is needed. To make sure we have an anchor PEB for the very first fastmap write we call ubi_ensure_anchor_pebs() during initialisation as well.

Fixes: 2e8f08deabbc ("ubi: Fix races around ubi_refill_pools()") Signed-off-by: Sascha Hauer s.hauer@pengutronix.de Signed-off-by: Richard Weinberger richard@nod.at Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/mtd/ubi/fastmap-wl.c | 31 ++++++++++++++++++------------- drivers/mtd/ubi/fastmap.c | 14 +++++--------- drivers/mtd/ubi/ubi.h | 6 ++++-- drivers/mtd/ubi/wl.c | 32 ++++++++++++++------------------ drivers/mtd/ubi/wl.h | 1 - 5 files changed, 41 insertions(+), 43 deletions(-)

diff --git a/drivers/mtd/ubi/fastmap-wl.c b/drivers/mtd/ubi/fastmap-wl.c index 98f7d6be8d1f..13efebb40022 100644 --- a/drivers/mtd/ubi/fastmap-wl.c +++ b/drivers/mtd/ubi/fastmap-wl.c @@ -66,18 +66,6 @@ static void return_unused_pool_pebs(struct ubi_device *ubi, } }

-static int anchor_pebs_available(struct rb_root *root) -{ - struct rb_node *p; - struct ubi_wl_entry *e; - - ubi_rb_for_each_entry(p, e, root, u.rb) - if (e->pnum < UBI_FM_MAX_START) - return 1; - - return 0; -} - /** * ubi_wl_get_fm_peb - find a physical erase block with a given maximal number. * @ubi: UBI device description object @@ -286,8 +274,26 @@ static struct ubi_wl_entry *get_peb_for_wl(struct ubi_device *ubi) int ubi_ensure_anchor_pebs(struct ubi_device *ubi) { struct ubi_work *wrk; + struct ubi_wl_entry *anchor;

spin_lock(&ubi->wl_lock); + + /* Do we already have an anchor? */ + if (ubi->fm_anchor) { + spin_unlock(&ubi->wl_lock); + return 0; + } + + /* See if we can find an anchor PEB on the list of free PEBs */ + anchor = ubi_wl_get_fm_peb(ubi, 1); + if (anchor) { + ubi->fm_anchor = anchor; + spin_unlock(&ubi->wl_lock); + return 0; + } + + /* No luck, trigger wear leveling to produce a new anchor PEB */ + ubi->fm_do_produce_anchor = 1; if (ubi->wl_scheduled) { spin_unlock(&ubi->wl_lock); return 0; @@ -303,7 +309,6 @@ int ubi_ensure_anchor_pebs(struct ubi_device *ubi) return -ENOMEM; }

- wrk->anchor = 1; wrk->func = &wear_leveling_worker; __schedule_ubi_work(ubi, wrk); return 0; diff --git a/drivers/mtd/ubi/fastmap.c b/drivers/mtd/ubi/fastmap.c index 8e292992f84c..b88ef875236c 100644 --- a/drivers/mtd/ubi/fastmap.c +++ b/drivers/mtd/ubi/fastmap.c @@ -1552,14 +1552,6 @@ int ubi_update_fastmap(struct ubi_device *ubi) return 0; }

- ret = ubi_ensure_anchor_pebs(ubi); - if (ret) { - up_write(&ubi->fm_eba_sem); - up_write(&ubi->work_sem); - up_write(&ubi->fm_protect); - return ret; - } - new_fm = kzalloc(sizeof(*new_fm), GFP_KERNEL); if (!new_fm) { up_write(&ubi->fm_eba_sem); @@ -1630,7 +1622,8 @@ int ubi_update_fastmap(struct ubi_device *ubi) }

spin_lock(&ubi->wl_lock); - tmp_e = ubi_wl_get_fm_peb(ubi, 1); + tmp_e = ubi->fm_anchor; + ubi->fm_anchor = NULL; spin_unlock(&ubi->wl_lock);

if (old_fm) { @@ -1682,6 +1675,9 @@ int ubi_update_fastmap(struct ubi_device *ubi) up_write(&ubi->work_sem); up_write(&ubi->fm_protect); kfree(old_fm); + + ubi_ensure_anchor_pebs(ubi); + return ret;

err: diff --git a/drivers/mtd/ubi/ubi.h b/drivers/mtd/ubi/ubi.h index d47b9e436e67..d248ec371cc1 100644 --- a/drivers/mtd/ubi/ubi.h +++ b/drivers/mtd/ubi/ubi.h @@ -504,6 +504,8 @@ struct ubi_debug_info { * @fm_work: fastmap work queue * @fm_work_scheduled: non-zero if fastmap work was scheduled * @fast_attach: non-zero if UBI was attached by fastmap + * @fm_anchor: The next anchor PEB to use for fastmap + * @fm_do_produce_anchor: If true produce an anchor PEB in wl * * @used: RB-tree of used physical eraseblocks * @erroneous: RB-tree of erroneous used physical eraseblocks @@ -612,6 +614,8 @@ struct ubi_device { struct work_struct fm_work; int fm_work_scheduled; int fast_attach; + struct ubi_wl_entry *fm_anchor; + int fm_do_produce_anchor;

/* Wear-leveling sub-system's stuff */ struct rb_root used; @@ -802,7 +806,6 @@ struct ubi_attach_info { * @vol_id: the volume ID on which this erasure is being performed * @lnum: the logical eraseblock number * @torture: if the physical eraseblock has to be tortured - * @anchor: produce a anchor PEB to by used by fastmap * * The @func pointer points to the worker function. If the @shutdown argument is * not zero, the worker has to free the resources and exit immediately as the @@ -818,7 +821,6 @@ struct ubi_work { int vol_id; int lnum; int torture; - int anchor; };

#include "debug.h" diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c index 6f2ac865ff05..80d64d7e7a8b 100644 --- a/drivers/mtd/ubi/wl.c +++ b/drivers/mtd/ubi/wl.c @@ -331,13 +331,6 @@ static struct ubi_wl_entry *find_wl_entry(struct ubi_device *ubi, } }

- /* If no fastmap has been written and this WL entry can be used - * as anchor PEB, hold it back and return the second best WL entry - * such that fastmap can use the anchor PEB later. */ - if (prev_e && !ubi->fm_disabled && - !ubi->fm && e->pnum < UBI_FM_MAX_START) - return prev_e; - return e; }

@@ -648,9 +641,6 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, { int err, scrubbing = 0, torture = 0, protect = 0, erroneous = 0; int erase = 0, keep = 0, vol_id = -1, lnum = -1; -#ifdef CONFIG_MTD_UBI_FASTMAP - int anchor = wrk->anchor; -#endif struct ubi_wl_entry *e1, *e2; struct ubi_vid_io_buf *vidb; struct ubi_vid_hdr *vid_hdr; @@ -690,11 +680,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, }

#ifdef CONFIG_MTD_UBI_FASTMAP - /* Check whether we need to produce an anchor PEB */ - if (!anchor) - anchor = !anchor_pebs_available(&ubi->free); - - if (anchor) { + if (ubi->fm_do_produce_anchor) { e1 = find_anchor_wl_entry(&ubi->used); if (!e1) goto out_cancel; @@ -705,6 +691,7 @@ static int wear_leveling_worker(struct ubi_device *ubi, struct ubi_work *wrk, self_check_in_wl_tree(ubi, e1, &ubi->used); rb_erase(&e1->u.rb, &ubi->used); dbg_wl("anchor-move PEB %d to PEB %d", e1->pnum, e2->pnum); + ubi->fm_do_produce_anchor = 0; } else if (!ubi->scrub.rb_node) { #else if (!ubi->scrub.rb_node) { @@ -1037,7 +1024,6 @@ static int ensure_wear_leveling(struct ubi_device *ubi, int nested) goto out_cancel; }

- wrk->anchor = 0; wrk->func = &wear_leveling_worker; if (nested) __schedule_ubi_work(ubi, wrk); @@ -1079,8 +1065,15 @@ static int __erase_worker(struct ubi_device *ubi, struct ubi_work *wl_wrk) err = sync_erase(ubi, e, wl_wrk->torture); if (!err) { spin_lock(&ubi->wl_lock); - wl_tree_add(e, &ubi->free); - ubi->free_count++; + + if (!ubi->fm_anchor && e->pnum < UBI_FM_MAX_START) { + ubi->fm_anchor = e; + ubi->fm_do_produce_anchor = 0; + } else { + wl_tree_add(e, &ubi->free); + ubi->free_count++; + } + spin_unlock(&ubi->wl_lock);

/* @@ -1724,6 +1717,9 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai) if (err) goto out_free;

+#ifdef CONFIG_MTD_UBI_FASTMAP + ubi_ensure_anchor_pebs(ubi); +#endif return 0;

out_free: diff --git a/drivers/mtd/ubi/wl.h b/drivers/mtd/ubi/wl.h index a9e2d669acd8..c93a53293786 100644 --- a/drivers/mtd/ubi/wl.h +++ b/drivers/mtd/ubi/wl.h @@ -2,7 +2,6 @@ #ifndef UBI_WL_H #define UBI_WL_H #ifdef CONFIG_MTD_UBI_FASTMAP -static int anchor_pebs_available(struct rb_root *root); static void update_fastmap_work_fn(struct work_struct *wrk); static struct ubi_wl_entry *find_anchor_wl_entry(struct rb_root *root); static struct ubi_wl_entry *get_peb_for_wl(struct ubi_device *ubi);

From: Bob Peterson rpeterso@redhat.com

[ Upstream commit 2c47c1be51fbded1f7baa2ceaed90f97932f79be ]

Before this patch, gfs2_create_inode had a use-after-free for the iopen glock in some error paths because it did this:

gfs2_glock_put(io_gl); fail_gunlock2: if (io_gl) clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);

In some cases, the io_gl was used for create and only had one reference, so the glock might be freed before the clear_bit(). This patch tries to straighten it out by only jumping to the error paths where iopen is properly set, and moving the gfs2_glock_put after the clear_bit.

Signed-off-by: Bob Peterson rpeterso@redhat.com Signed-off-by: Andreas Gruenbacher agruenba@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/gfs2/inode.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-)

diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index d968b5c5df21..a52b8b0dceeb 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -715,7 +715,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,

error = gfs2_trans_begin(sdp, blocks, 0); if (error) - goto fail_gunlock2; + goto fail_free_inode;

if (blocks > 1) { ip->i_eattr = ip->i_no_addr + 1; @@ -726,7 +726,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,

error = gfs2_glock_get(sdp, ip->i_no_addr, &gfs2_iopen_glops, CREATE, &io_gl); if (error) - goto fail_gunlock2; + goto fail_free_inode;

BUG_ON(test_and_set_bit(GLF_INODE_CREATING, &io_gl->gl_flags));

@@ -735,7 +735,6 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, goto fail_gunlock2;

glock_set_object(ip->i_iopen_gh.gh_gl, ip); - gfs2_glock_put(io_gl); gfs2_set_iop(inode); insert_inode_hash(inode);

@@ -768,6 +767,8 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,

mark_inode_dirty(inode); d_instantiate(dentry, inode); + /* After instantiate, errors should result in evict which will destroy + * both inode and iopen glocks properly. */ if (file) { file->f_mode |= FMODE_CREATED; error = finish_open(file, dentry, gfs2_open_common); @@ -775,15 +776,15 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry, gfs2_glock_dq_uninit(ghs); gfs2_glock_dq_uninit(ghs + 1); clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); + gfs2_glock_put(io_gl); return error;

fail_gunlock3: glock_clear_object(io_gl, ip); gfs2_glock_dq_uninit(&ip->i_iopen_gh); - gfs2_glock_put(io_gl); fail_gunlock2: - if (io_gl) - clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); + clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags); + gfs2_glock_put(io_gl); fail_free_inode: if (ip->i_gl) { glock_clear_object(ip->i_gl, ip);

From: Kusanagi Kouichi slash@ac.auone-net.jp

[ Upstream commit 4250b047039d324e0ff65267c8beb5bad5052a86 ]

If DEBUG_FS=n, compile fails with the following error:

kernel/trace/trace.c: In function 'tracing_init_dentry': kernel/trace/trace.c:8658:9: error: passing argument 3 of 'debugfs_create_automount' from incompatible pointer type [-Werror=incompatible-pointer-types] 8658 | trace_automount, NULL); | ^~~~~~~~~~~~~~~ | | | struct vfsmount * (*)(struct dentry *, void *) In file included from kernel/trace/trace.c:24: ./include/linux/debugfs.h:206:25: note: expected 'struct vfsmount * (*)(void *)' but argument is of type 'struct vfsmount * (*)(struct dentry *, void *)' 206 | struct vfsmount *(*f)(void *), | ~~~~~~~~~~~~~~~~~~~^~~~~~~~~~

Signed-off-by: Kusanagi Kouichi slash@ac.auone-net.jp Link: https://lore.kernel.org/r/20191121102021787.MLMY.25002.ppp.dion.ne.jp@dmta00... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- include/linux/debugfs.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h index 5fdcfeff9308..4ca5d12f57f1 100644 --- a/include/linux/debugfs.h +++ b/include/linux/debugfs.h @@ -54,6 +54,8 @@ static const struct file_operations __fops = { \ .llseek = no_llseek, \ }

+typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *); + #if defined(CONFIG_DEBUG_FS)

struct dentry *debugfs_lookup(const char *name, struct dentry *parent); @@ -75,7 +77,6 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent); struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *dest);

-typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *); struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, debugfs_automount_t f, @@ -204,7 +205,7 @@ static inline struct dentry *debugfs_create_symlink(const char *name,

static inline struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, - struct vfsmount *(*f)(void *), + debugfs_automount_t f, void *data) { return ERR_PTR(-ENODEV);

From: Tzung-Bi Shih tzungbi@google.com

[ Upstream commit acb874a7c049ec49d8fc66c893170fb42c01bdf7 ]

It was observed Baytrail-based chromebooks could cause continuous PLL unlocked when using playback stream and capture stream simultaneously. Specifically, starting a capture stream after started a playback stream. As a result, the audio data could corrupt or turn completely silent.

As the datasheet suggested, the maximum PLL lock time should be 7 msec. The workaround resets the codec softly by toggling SHDN off and on if PLL failed to lock for 10 msec. Notably, there is no suggested hold time for SHDN off.

On Baytrail-based chromebooks, it would easily happen continuous PLL unlocked if there is a 10 msec delay between SHDN off and on. Removes the msleep().

Signed-off-by: Tzung-Bi Shih tzungbi@google.com Link: https://lore.kernel.org/r/20191122073114.219945-2-tzungbi@google.com Reviewed-by: Pierre-Louis Bossart pierre-louis.bossart@linux.intel.com Signed-off-by: Mark Brown broonie@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- sound/soc/codecs/max98090.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/sound/soc/codecs/max98090.c b/sound/soc/codecs/max98090.c index 89b6e187ac23..a5b0c40ee545 100644 --- a/sound/soc/codecs/max98090.c +++ b/sound/soc/codecs/max98090.c @@ -2130,10 +2130,16 @@ static void max98090_pll_work(struct max98090_priv *max98090)

dev_info_ratelimited(component->dev, "PLL unlocked\n");

+ /* + * As the datasheet suggested, the maximum PLL lock time should be + * 7 msec. The workaround resets the codec softly by toggling SHDN + * off and on if PLL failed to lock for 10 msec. Notably, there is + * no suggested hold time for SHDN off. + */ + /* Toggle shutdown OFF then ON */ snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, M98090_SHDNN_MASK, 0); - msleep(10); snd_soc_component_update_bits(component, M98090_REG_DEVICE_SHUTDOWN, M98090_SHDNN_MASK, M98090_SHDNN_MASK);

From: Miaohe Lin linmiaohe@huawei.com

[ Upstream commit 0bda9498dd45280e334bfe88b815ebf519602cc3 ]

In kvm_vgic_dist_init() called from kvm_vgic_map_resources(), if dist->vgic_model is invalid, dist->spis will be freed without set dist->spis = NULL. And in vgicv2 resources clean up path, __kvm_vgic_destroy() will be called to free allocated resources. And dist->spis will be freed again in clean up chain because we forget to set dist->spis = NULL in kvm_vgic_dist_init() failed path. So double free would happen.

Signed-off-by: Miaohe Lin linmiaohe@huawei.com Signed-off-by: Marc Zyngier maz@kernel.org Reviewed-by: Eric Auger eric.auger@redhat.com Link: https://lore.kernel.org/r/1574923128-19956-1-git-send-email-linmiaohe@huawei... Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- virt/kvm/arm/vgic/vgic-init.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/virt/kvm/arm/vgic/vgic-init.c b/virt/kvm/arm/vgic/vgic-init.c index cd991396dd78..1f39c61428f9 100644 --- a/virt/kvm/arm/vgic/vgic-init.c +++ b/virt/kvm/arm/vgic/vgic-init.c @@ -194,6 +194,7 @@ static int kvm_vgic_dist_init(struct kvm *kvm, unsigned int nr_spis) break; default: kfree(dist->spis); + dist->spis = NULL; return -EINVAL; } }

From: Vasily Averin vvs@virtuozzo.com

[ Upstream commit 1e3f9f073c47bee7c23e77316b07bc12338c5bba ]

if seq_file .next fuction does not change position index, read after some lseek can generate unexpected output.

https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin vvs@virtuozzo.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- net/core/neighbour.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/core/neighbour.c b/net/core/neighbour.c index bf738ec68cb5..6e890f51b7d8 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2844,6 +2844,7 @@ static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1; return per_cpu_ptr(tbl->stats, cpu); } + (*pos)++; return NULL; }

From: Vasily Averin vvs@virtuozzo.com

[ Upstream commit 4fc427e0515811250647d44de38d87d7b0e0790f ]

if seq_file .next fuction does not change position index, read after some lseek can generate unexpected output.

https://bugzilla.kernel.org/show_bug.cgi?id=206283 Signed-off-by: Vasily Averin vvs@virtuozzo.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- net/ipv6/ip6_fib.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 05a206202e23..b924941b96a3 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -2377,14 +2377,13 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private;

+ ++(*pos); if (!v) goto iter_table;

n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); - if (n) { - ++*pos; + if (n) return n; - }

iter_table: ipv6_route_check_sernum(iter); @@ -2392,8 +2391,6 @@ static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) r = fib6_walk_continue(&iter->w); spin_unlock_bh(&iter->tbl->tb6_lock); if (r > 0) { - if (v) - ++*pos; return iter->w.leaf; } else if (r < 0) { fib6_walker_unlink(net, &iter->w);

From: Nikhil Devshatwar nikhil.nd@ti.com

[ Upstream commit 6e72eab2e7b7a157d554b8f9faed7676047be7c1 ]

When setting DMA for video capture from CSI channel, if the DMA size is not given, it ends up writing as much data as sent by the camera.

This may lead to overwriting the buffers causing memory corruption. Observed green lines on the default framebuffer.

Restrict the DMA to maximum height as specified in the S_FMT ioctl.

Signed-off-by: Nikhil Devshatwar nikhil.nd@ti.com Signed-off-by: Benoit Parrot bparrot@ti.com Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+huawei@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/media/platform/ti-vpe/cal.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/media/platform/ti-vpe/cal.c b/drivers/media/platform/ti-vpe/cal.c index be3155275a6b..d945323fc437 100644 --- a/drivers/media/platform/ti-vpe/cal.c +++ b/drivers/media/platform/ti-vpe/cal.c @@ -684,12 +684,13 @@ static void pix_proc_config(struct cal_ctx *ctx) }

static void cal_wr_dma_config(struct cal_ctx *ctx, - unsigned int width) + unsigned int width, unsigned int height) { u32 val;

val = reg_read(ctx->dev, CAL_WR_DMA_CTRL(ctx->csi2_port)); set_field(&val, ctx->csi2_port, CAL_WR_DMA_CTRL_CPORT_MASK); + set_field(&val, height, CAL_WR_DMA_CTRL_YSIZE_MASK); set_field(&val, CAL_WR_DMA_CTRL_DTAG_PIX_DAT, CAL_WR_DMA_CTRL_DTAG_MASK); set_field(&val, CAL_WR_DMA_CTRL_MODE_CONST, @@ -1315,7 +1316,8 @@ static int cal_start_streaming(struct vb2_queue *vq, unsigned int count) csi2_lane_config(ctx); csi2_ctx_config(ctx); pix_proc_config(ctx); - cal_wr_dma_config(ctx, ctx->v_fmt.fmt.pix.bytesperline); + cal_wr_dma_config(ctx, ctx->v_fmt.fmt.pix.bytesperline, + ctx->v_fmt.fmt.pix.height); cal_wr_dma_addr(ctx, addr); csi2_ppi_enable(ctx);

From: "Rafael J. Wysocki" rafael.j.wysocki@intel.com

[ Upstream commit 3df663a147fe077a6ee8444ec626738946e65547 ]

There is a race condition in acpi_ec_get_query_handler() theoretically allowing query handlers to go away before refernce counting them.

In order to avoid it, call kref_get() on query handlers under ec->mutex.

Also simplify the code a bit while at it.

Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/acpi/ec.c | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-)

diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index 49e16f009095..9415a0041aaf 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1080,29 +1080,21 @@ void acpi_ec_dispatch_gpe(void) /* -------------------------------------------------------------------------- Event Management -------------------------------------------------------------------------- */ -static struct acpi_ec_query_handler * -acpi_ec_get_query_handler(struct acpi_ec_query_handler *handler) -{ - if (handler) - kref_get(&handler->kref); - return handler; -} - static struct acpi_ec_query_handler * acpi_ec_get_query_handler_by_value(struct acpi_ec *ec, u8 value) { struct acpi_ec_query_handler *handler; - bool found = false;

mutex_lock(&ec->mutex); list_for_each_entry(handler, &ec->list, node) { if (value == handler->query_bit) { - found = true; - break; + kref_get(&handler->kref); + mutex_unlock(&ec->mutex); + return handler; } } mutex_unlock(&ec->mutex); - return found ? acpi_ec_get_query_handler(handler) : NULL; + return NULL; }

static void acpi_ec_query_handler_release(struct kref *kref)

From: Bart Van Assche bvanassche@acm.org

[ Upstream commit eacf36f5bebde5089dddb3d5bfcbeab530b01f8a ]

Starting execution of a command before tracing a command may cause the completion handler to free data while it is being traced. Fix this race by tracing a command before it is submitted.

Cc: Bean Huo beanhuo@micron.com Cc: Can Guo cang@codeaurora.org Cc: Avri Altman avri.altman@wdc.com Cc: Stanley Chu stanley.chu@mediatek.com Cc: Tomas Winkler tomas.winkler@intel.com Link: https://lore.kernel.org/r/20191224220248.30138-5-bvanassche@acm.org Reviewed-by: Alim Akhtar alim.akhtar@samsung.com Signed-off-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/scsi/ufs/ufshcd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index faf195998178..b2cbdd01ab10 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -1910,12 +1910,12 @@ void ufshcd_send_command(struct ufs_hba *hba, unsigned int task_tag) { hba->lrb[task_tag].issue_time_stamp = ktime_get(); hba->lrb[task_tag].compl_time_stamp = ktime_set(0, 0); + ufshcd_add_command_trace(hba, task_tag, "send"); ufshcd_clk_scaling_start_busy(hba); __set_bit(task_tag, &hba->outstanding_reqs); ufshcd_writel(hba, 1 << task_tag, REG_UTP_TRANSFER_REQ_DOOR_BELL); /* Make sure that doorbell is committed immediately */ wmb(); - ufshcd_add_command_trace(hba, task_tag, "send"); }

/**

From: Thomas Richter tmricht@linux.ibm.com

[ Upstream commit 32dab6828c42f087439d3e2617dc7283546bd8f7 ]

Use kzalloc() to allocate auxiliary buffer structure initialized with all zeroes to avoid random value in trace output.

Avoid double access to SBD hardware flags.

Signed-off-by: Thomas Richter tmricht@linux.ibm.com Signed-off-by: Vasily Gorbik gor@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- arch/s390/kernel/perf_cpum_sf.c | 9 ++++----- 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c index 74a296cea21c..0e6d01225a67 100644 --- a/arch/s390/kernel/perf_cpum_sf.c +++ b/arch/s390/kernel/perf_cpum_sf.c @@ -1377,8 +1377,8 @@ static int aux_output_begin(struct perf_output_handle *handle, idx = aux->empty_mark + 1; for (i = 0; i < range_scan; i++, idx++) { te = aux_sdb_trailer(aux, idx); - te->flags = te->flags & ~SDB_TE_BUFFER_FULL_MASK; - te->flags = te->flags & ~SDB_TE_ALERT_REQ_MASK; + te->flags &= ~(SDB_TE_BUFFER_FULL_MASK | + SDB_TE_ALERT_REQ_MASK); te->overflow = 0; } /* Save the position of empty SDBs */ @@ -1425,8 +1425,7 @@ static bool aux_set_alert(struct aux_buffer *aux, unsigned long alert_index, te = aux_sdb_trailer(aux, alert_index); do { orig_flags = te->flags; - orig_overflow = te->overflow; - *overflow = orig_overflow; + *overflow = orig_overflow = te->overflow; if (orig_flags & SDB_TE_BUFFER_FULL_MASK) { /* * SDB is already set by hardware. @@ -1660,7 +1659,7 @@ static void *aux_buffer_setup(struct perf_event *event, void **pages, }

/* Allocate aux_buffer struct for the event */ - aux = kmalloc(sizeof(struct aux_buffer), GFP_KERNEL); + aux = kzalloc(sizeof(struct aux_buffer), GFP_KERNEL); if (!aux) goto no_aux; sfb = &aux->sfb;

From: Maxim Mikityanskiy maxtram95@gmail.com

[ Upstream commit 268d3636dfb22254324774de1f8875174b3be064 ]

Currently, kmemdup is applied to the firmware data, and it invokes kmalloc under the hood. The firmware size and patch_length are big (more than PAGE_SIZE), and on some low-end systems (like ASUS E202SA) kmalloc may fail to allocate a contiguous chunk under high memory usage and fragmentation:

Bluetooth: hci0: RTL: examining hci_ver=06 hci_rev=000a lmp_ver=06 lmp_subver=8821 Bluetooth: hci0: RTL: rom_version status=0 version=1 Bluetooth: hci0: RTL: loading rtl_bt/rtl8821a_fw.bin kworker/u9:2: page allocation failure: order:4, mode:0x40cc0(GFP_KERNEL|__GFP_COMP), nodemask=(null),cpuset=/,mems_allowed=0 <stack trace follows>

As firmware load happens on each resume, Bluetooth will stop working after several iterations, when the kernel fails to allocate an order-4 page.

This patch replaces kmemdup with kvmalloc+memcpy. It's not required to have a contiguous chunk here, because it's not mapped to the device directly.

Signed-off-by: Maxim Mikityanskiy maxtram95@gmail.com Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/bluetooth/btrtl.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-)

diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c index 8d1cd2479e36..cc51395d8b0e 100644 --- a/drivers/bluetooth/btrtl.c +++ b/drivers/bluetooth/btrtl.c @@ -343,11 +343,11 @@ static int rtlbt_parse_firmware(struct hci_dev *hdev, * the end. */ len = patch_length; - buf = kmemdup(btrtl_dev->fw_data + patch_offset, patch_length, - GFP_KERNEL); + buf = kvmalloc(patch_length, GFP_KERNEL); if (!buf) return -ENOMEM;

+ memcpy(buf, btrtl_dev->fw_data + patch_offset, patch_length - 4); memcpy(buf + patch_length - 4, &epatch_info->fw_version, 4);

*_buf = buf; @@ -415,8 +415,10 @@ static int rtl_load_file(struct hci_dev *hdev, const char *name, u8 **buff) if (ret < 0) return ret; ret = fw->size; - *buff = kmemdup(fw->data, ret, GFP_KERNEL); - if (!*buff) + *buff = kvmalloc(fw->size, GFP_KERNEL); + if (*buff) + memcpy(*buff, fw->data, ret); + else ret = -ENOMEM;

release_firmware(fw); @@ -454,14 +456,14 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, goto out;

if (btrtl_dev->cfg_len > 0) { - tbuff = kzalloc(ret + btrtl_dev->cfg_len, GFP_KERNEL); + tbuff = kvzalloc(ret + btrtl_dev->cfg_len, GFP_KERNEL); if (!tbuff) { ret = -ENOMEM; goto out; }

memcpy(tbuff, fw_data, ret); - kfree(fw_data); + kvfree(fw_data);

memcpy(tbuff + ret, btrtl_dev->cfg_data, btrtl_dev->cfg_len); ret += btrtl_dev->cfg_len; @@ -474,7 +476,7 @@ static int btrtl_setup_rtl8723b(struct hci_dev *hdev, ret = rtl_download_firmware(hdev, fw_data, ret);

out: - kfree(fw_data); + kvfree(fw_data); return ret; }

@@ -501,8 +503,8 @@ static struct sk_buff *btrtl_read_local_version(struct hci_dev *hdev)

void btrtl_free(struct btrtl_device_info *btrtl_dev) { - kfree(btrtl_dev->fw_data); - kfree(btrtl_dev->cfg_data); + kvfree(btrtl_dev->fw_data); + kvfree(btrtl_dev->cfg_data); kfree(btrtl_dev); } EXPORT_SYMBOL_GPL(btrtl_free);

From: Vincent Whitchurch vincent.whitchurch@axis.com

[ Upstream commit 40ff1ddb5570284e039e0ff14d7a859a73dc3673 ]

The stacktrace code can read beyond the stack size, when it attempts to read pt_regs from exception frames.

This can happen on normal, non-corrupt stacks. Since the unwind information in the extable is not correct for function prologues, the unwinding code can return data from the stack which is not actually the caller function address, and if in_entry_text() happens to succeed on this value, we can end up reading data from outside the task's stack when attempting to read pt_regs, since there is no bounds check.

Example:

[<8010e729>] (unwind_backtrace) from [<8010a9c9>] (show_stack+0x11/0x14) [<8010a9c9>] (show_stack) from [<8057d8d7>] (dump_stack+0x87/0xac) [<8057d8d7>] (dump_stack) from [<8012271d>] (tasklet_action_common.constprop.4+0xa5/0xa8) [<8012271d>] (tasklet_action_common.constprop.4) from [<80102333>] (__do_softirq+0x11b/0x31c) [<80102333>] (__do_softirq) from [<80122485>] (irq_exit+0xad/0xd8) [<80122485>] (irq_exit) from [<8015f3d7>] (__handle_domain_irq+0x47/0x84) [<8015f3d7>] (__handle_domain_irq) from [<8036a523>] (gic_handle_irq+0x43/0x78) [<8036a523>] (gic_handle_irq) from [<80101a49>] (__irq_svc+0x69/0xb4) Exception stack(0xeb491f58 to 0xeb491fa0) 1f40: 7eb14794 00000000 1f60: ffffffff 008dd32c 008dd324 ffffffff 008dd314 0000002a 801011e4 eb490000 1f80: 0000002a 7eb1478c 50c5387d eb491fa8 80101001 8023d09c 40080033 ffffffff [<80101a49>] (__irq_svc) from [<8023d09c>] (do_pipe2+0x0/0xac) [<8023d09c>] (do_pipe2) from [<ffffffff>] (0xffffffff) Exception stack(0xeb491fc8 to 0xeb492010) 1fc0: 008dd314 0000002a 00511ad8 008de4c8 7eb14790 7eb1478c 1fe0: 00511e34 7eb14774 004c8557 76f44098 60080030 7eb14794 00000000 00000000 2000: 00000001 00000000 ea846c00 ea847cc0

In this example, the stack limit is 0xeb492000, but 16 bytes outside the stack have been read.

Fix it by adding bounds checks.

Signed-off-by: Vincent Whitchurch vincent.whitchurch@axis.com Signed-off-by: Russell King rmk+kernel@armlinux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- arch/arm/kernel/stacktrace.c | 2 ++ arch/arm/kernel/traps.c | 6 ++++-- 2 files changed, 6 insertions(+), 2 deletions(-)

diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c index a4d4a28fe07d..d23ab9ec130a 100644 --- a/arch/arm/kernel/stacktrace.c +++ b/arch/arm/kernel/stacktrace.c @@ -115,6 +115,8 @@ static int save_trace(struct stackframe *frame, void *d) return 0;

regs = (struct pt_regs *)frame->sp; + if ((unsigned long)&regs[1] > ALIGN(frame->sp, THREAD_SIZE)) + return 0;

trace->entries[trace->nr_entries++] = regs->ARM_pc;

diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c index 2a21239aec91..882c1b0cd931 100644 --- a/arch/arm/kernel/traps.c +++ b/arch/arm/kernel/traps.c @@ -67,14 +67,16 @@ static void dump_mem(const char *, const char *, unsigned long, unsigned long);

void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame) { + unsigned long end = frame + 4 + sizeof(struct pt_regs); + #ifdef CONFIG_KALLSYMS printk("[<%08lx>] (%ps) from [<%08lx>] (%pS)\n", where, (void *)where, from, (void *)from); #else printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from); #endif

- if (in_entry_text(from)) - dump_mem("", "Exception stack", frame + 4, frame + 4 + sizeof(struct pt_regs)); + if (in_entry_text(from) && end <= ALIGN(frame, THREAD_SIZE)) + dump_mem("", "Exception stack", frame + 4, end); }

void dump_backtrace_stm(u32 *stack, u32 instruction)

From: Jeff Layton jlayton@kernel.org

[ Upstream commit 9a6bed4fe0c8bf57785cbc4db9f86086cb9b193d ]

If the caller passes in a NULL cap_reservation, and we can't allocate one then ensure that we fail gracefully.

Signed-off-by: Jeff Layton jlayton@kernel.org Signed-off-by: Ilya Dryomov idryomov@gmail.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/ceph/inode.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c index 1e438e0faf77..3c24fb77ef32 100644 --- a/fs/ceph/inode.c +++ b/fs/ceph/inode.c @@ -764,8 +764,11 @@ static int fill_inode(struct inode *inode, struct page *locked_page, info_caps = le32_to_cpu(info->cap.caps);

/* prealloc new cap struct */ - if (info_caps && ceph_snap(inode) == CEPH_NOSNAP) + if (info_caps && ceph_snap(inode) == CEPH_NOSNAP) { new_cap = ceph_get_cap(mdsc, caps_reservation); + if (!new_cap) + return -ENOMEM; + }

/* * prealloc xattr data, if it looks like we'll need it. only

From: Doug Smythies doug.smythies@gmail.com

[ Upstream commit e749e09db30c38f1a275945814b0109e530a07b0 ]

Some syntax needs to be more rigorous for python 3. Backwards compatibility tested with python 2.7

Signed-off-by: Doug Smythies dsmythies@telus.net Signed-off-by: Rafael J. Wysocki rafael.j.wysocki@intel.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- .../intel_pstate_tracer.py | 22 +++++++++---------- 1 file changed, 11 insertions(+), 11 deletions(-)

diff --git a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py index 2fa3c5757bcb..dbed3d213bf1 100755 --- a/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py +++ b/tools/power/x86/intel_pstate_tracer/intel_pstate_tracer.py @@ -10,11 +10,11 @@ then this utility enables and collects trace data for a user specified interval and generates performance plots.

Prerequisites: - Python version 2.7.x + Python version 2.7.x or higher gnuplot 5.0 or higher - gnuplot-py 1.8 + gnuplot-py 1.8 or higher (Most of the distributions have these required packages. They may be called - gnuplot-py, phython-gnuplot. ) + gnuplot-py, phython-gnuplot or phython3-gnuplot, gnuplot-nox, ... )

HWP (Hardware P-States are disabled) Kernel config for Linux trace is enabled @@ -180,7 +180,7 @@ def plot_pstate_cpu_with_sample(): g_plot('set xlabel "Samples"') g_plot('set ylabel "P-State"') g_plot('set title "{} : cpu pstate vs. sample : {:%F %H:%M}"'.format(testname, datetime.now())) - title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_SAMPLE, C_TO) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -197,7 +197,7 @@ def plot_pstate_cpu(): # the following command is really cool, but doesn't work with the CPU masking option because it aborts on the first missing file. # plot_str = 'plot for [i=0:*] file=sprintf("cpu%03d.csv",i) title_s=sprintf("cpu%03d",i) file using 16:7 pt 7 ps 1 title title_s' # - title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_TO) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -211,7 +211,7 @@ def plot_load_cpu(): g_plot('set ylabel "CPU load (percent)"') g_plot('set title "{} : cpu loads : {:%F %H:%M}"'.format(testname, datetime.now()))

- title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_LOAD) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -225,7 +225,7 @@ def plot_frequency_cpu(): g_plot('set ylabel "CPU Frequency (GHz)"') g_plot('set title "{} : cpu frequencies : {:%F %H:%M}"'.format(testname, datetime.now()))

- title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_FREQ) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -240,7 +240,7 @@ def plot_duration_cpu(): g_plot('set ylabel "Timer Duration (MilliSeconds)"') g_plot('set title "{} : cpu durations : {:%F %H:%M}"'.format(testname, datetime.now()))

- title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_DURATION) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -254,7 +254,7 @@ def plot_scaled_cpu(): g_plot('set ylabel "Scaled Busy (Unitless)"') g_plot('set title "{} : cpu scaled busy : {:%F %H:%M}"'.format(testname, datetime.now()))

- title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_SCALED) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -268,7 +268,7 @@ def plot_boost_cpu(): g_plot('set ylabel "CPU IO Boost (percent)"') g_plot('set title "{} : cpu io boost : {:%F %H:%M}"'.format(testname, datetime.now()))

- title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_BOOST) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str) @@ -282,7 +282,7 @@ def plot_ghz_cpu(): g_plot('set ylabel "TSC Frequency (GHz)"') g_plot('set title "{} : cpu TSC Frequencies (Sanity check calculation) : {:%F %H:%M}"'.format(testname, datetime.now()))

- title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).replace('\n', ' ') + title_list = subprocess.check_output('ls cpu???.csv | sed -e 's/.csv//'',shell=True).decode('utf-8').replace('\n', ' ') plot_str = "plot for [i in title_list] i.'.csv' using {:d}:{:d} pt 7 ps 1 title i".format(C_ELAPSED, C_GHZ) g_plot('title_list = "{}"'.format(title_list)) g_plot(plot_str)

From: Vasily Averin vvs@virtuozzo.com

[ Upstream commit 10c8d69f314d557d94d74ec492575ae6a4f1eb1c ]

If seq_file .next fuction does not change position index, read after some lseek can generate unexpected output.

In Aug 2018 NeilBrown noticed commit 1f4aace60b0e ("fs/seq_file.c: simplify seq_file iteration code and interface") "Some ->next functions do not increment *pos when they return NULL... Note that such ->next functions are buggy and should be fixed. A simple demonstration is

dd if=/proc/swaps bs=1000 skip=1

Choose any block size larger than the size of /proc/swaps. This will always show the whole last line of /proc/swaps"

Described problem is still actual. If you make lseek into middle of last output line following read will output end of last line and whole last line once again.

$ dd if=/proc/swaps bs=1 # usual output Filename Type Size Used Priority /dev/dm-0 partition 4194812 97536 -2 104+0 records in 104+0 records out 104 bytes copied

$ dd if=/proc/swaps bs=40 skip=1 # last line was generated twice dd: /proc/swaps: cannot skip to specified offset v/dm-0 partition 4194812 97536 -2 /dev/dm-0 partition 4194812 97536 -2 3+1 records in 3+1 records out 131 bytes copied

https://bugzilla.kernel.org/show_bug.cgi?id=206283

Link: http://lkml.kernel.org/r/bd8cfd7b-ac95-9b91-f9e7-e8438bd5047d@virtuozzo.com Signed-off-by: Vasily Averin vvs@virtuozzo.com Reviewed-by: Andrew Morton akpm@linux-foundation.org Cc: Jann Horn jannh@google.com Cc: Alexander Viro viro@zeniv.linux.org.uk Cc: Kees Cook keescook@chromium.org Cc: Hugh Dickins hughd@google.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- mm/swapfile.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c index 41400ae4e7c1..765fca3451d2 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2843,10 +2843,10 @@ static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) else type = si->type + 1;

+ ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; - ++*pos; return si; }

From: Zhuang Yanying ann.zhuangyanying@huawei.com

[ Upstream commit 7df003c85218b5f5b10a7f6418208f31e813f38f ]

We are testing Virtual Machine with KSM on v5.4-rc2 kernel, and found the zero_page refcount overflow. The cause of refcount overflow is increased in try_async_pf (get_user_page) without being decreased in mmu_set_spte() while handling ept violation. In kvm_release_pfn_clean(), only unreserved page will call put_page. However, zero page is reserved. So, as well as creating and destroy vm, the refcount of zero page will continue to increase until it overflows.

step1: echo 10000 > /sys/kernel/pages_to_scan/pages_to_scan echo 1 > /sys/kernel/pages_to_scan/run echo 1 > /sys/kernel/pages_to_scan/use_zero_pages

step2: just create several normal qemu kvm vms. And destroy it after 10s. Repeat this action all the time.

After a long period of time, all domains hang because of the refcount of zero page overflow.

Qemu print error log as follow: … error: kvm run failed Bad address EAX=00006cdc EBX=00000008 ECX=80202001 EDX=078bfbfd ESI=ffffffff EDI=00000000 EBP=00000008 ESP=00006cc4 EIP=000efd75 EFL=00010002 [-------] CPL=0 II=0 A20=1 SMM=0 HLT=0 ES =0010 00000000 ffffffff 00c09300 DPL=0 DS [-WA] CS =0008 00000000 ffffffff 00c09b00 DPL=0 CS32 [-RA] SS =0010 00000000 ffffffff 00c09300 DPL=0 DS [-WA] DS =0010 00000000 ffffffff 00c09300 DPL=0 DS [-WA] FS =0010 00000000 ffffffff 00c09300 DPL=0 DS [-WA] GS =0010 00000000 ffffffff 00c09300 DPL=0 DS [-WA] LDT=0000 00000000 0000ffff 00008200 DPL=0 LDT TR =0000 00000000 0000ffff 00008b00 DPL=0 TSS32-busy GDT= 000f7070 00000037 IDT= 000f70ae 00000000 CR0=00000011 CR2=00000000 CR3=00000000 CR4=00000000 DR0=0000000000000000 DR1=0000000000000000 DR2=0000000000000000 DR3=0000000000000000 DR6=00000000ffff0ff0 DR7=0000000000000400 EFER=0000000000000000 Code=00 01 00 00 00 e9 e8 00 00 00 c7 05 4c 55 0f 00 01 00 00 00 <8b> 35 00 00 01 00 8b 3d 04 00 01 00 b8 d8 d3 00 00 c1 e0 08 0c ea a3 00 00 01 00 c7 05 04 …

Meanwhile, a kernel warning is departed.

[40914.836375] WARNING: CPU: 3 PID: 82067 at ./include/linux/mm.h:987 try_get_page+0x1f/0x30 [40914.836412] CPU: 3 PID: 82067 Comm: CPU 0/KVM Kdump: loaded Tainted: G OE 5.2.0-rc2 #5 [40914.836415] RIP: 0010:try_get_page+0x1f/0x30 [40914.836417] Code: 40 00 c3 0f 1f 84 00 00 00 00 00 48 8b 47 08 a8 01 75 11 8b 47 34 85 c0 7e 10 f0 ff 47 34 b8 01 00 00 00 c3 48 8d 78 ff eb e9 <0f> 0b 31 c0 c3 66 90 66 2e 0f 1f 84 00 0 0 00 00 00 48 8b 47 08 a8 [40914.836418] RSP: 0018:ffffb4144e523988 EFLAGS: 00010286 [40914.836419] RAX: 0000000080000000 RBX: 0000000000000326 RCX: 0000000000000000 [40914.836420] RDX: 0000000000000000 RSI: 00004ffdeba10000 RDI: ffffdf07093f6440 [40914.836421] RBP: ffffdf07093f6440 R08: 800000424fd91225 R09: 0000000000000000 [40914.836421] R10: ffff9eb41bfeebb8 R11: 0000000000000000 R12: ffffdf06bbd1e8a8 [40914.836422] R13: 0000000000000080 R14: 800000424fd91225 R15: ffffdf07093f6440 [40914.836423] FS: 00007fb60ffff700(0000) GS:ffff9eb4802c0000(0000) knlGS:0000000000000000 [40914.836425] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [40914.836426] CR2: 0000000000000000 CR3: 0000002f220e6002 CR4: 00000000003626e0 [40914.836427] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [40914.836427] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [40914.836428] Call Trace: [40914.836433] follow_page_pte+0x302/0x47b [40914.836437] __get_user_pages+0xf1/0x7d0 [40914.836441] ? irq_work_queue+0x9/0x70 [40914.836443] get_user_pages_unlocked+0x13f/0x1e0 [40914.836469] __gfn_to_pfn_memslot+0x10e/0x400 [kvm] [40914.836486] try_async_pf+0x87/0x240 [kvm] [40914.836503] tdp_page_fault+0x139/0x270 [kvm] [40914.836523] kvm_mmu_page_fault+0x76/0x5e0 [kvm] [40914.836588] vcpu_enter_guest+0xb45/0x1570 [kvm] [40914.836632] kvm_arch_vcpu_ioctl_run+0x35d/0x580 [kvm] [40914.836645] kvm_vcpu_ioctl+0x26e/0x5d0 [kvm] [40914.836650] do_vfs_ioctl+0xa9/0x620 [40914.836653] ksys_ioctl+0x60/0x90 [40914.836654] __x64_sys_ioctl+0x16/0x20 [40914.836658] do_syscall_64+0x5b/0x180 [40914.836664] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [40914.836666] RIP: 0033:0x7fb61cb6bfc7

Signed-off-by: LinFeng linfeng23@huawei.com Signed-off-by: Zhuang Yanying ann.zhuangyanying@huawei.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- virt/kvm/kvm_main.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 52f8d142d756..16c55b62f33d 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -169,6 +169,7 @@ bool kvm_is_reserved_pfn(kvm_pfn_t pfn) */ if (pfn_valid(pfn)) return PageReserved(pfn_to_page(pfn)) && + !is_zero_pfn(pfn) && !kvm_is_zone_device_pfn(pfn);

return true;

From: Qian Cai cai@lca.pw

[ Upstream commit 86b18aaa2b5b5bb48e609cd591b3d2d0fdbe0442 ]

sk_buff.qlen can be accessed concurrently as noticed by KCSAN,

BUG: KCSAN: data-race in __skb_try_recv_from_queue / unix_dgram_sendmsg

read to 0xffff8a1b1d8a81c0 of 4 bytes by task 5371 on cpu 96: unix_dgram_sendmsg+0x9a9/0xb70 include/linux/skbuff.h:1821 net/unix/af_unix.c:1761 ____sys_sendmsg+0x33e/0x370 ___sys_sendmsg+0xa6/0xf0 __sys_sendmsg+0x69/0xf0 __x64_sys_sendmsg+0x51/0x70 do_syscall_64+0x91/0xb47 entry_SYSCALL_64_after_hwframe+0x49/0xbe

write to 0xffff8a1b1d8a81c0 of 4 bytes by task 1 on cpu 99: __skb_try_recv_from_queue+0x327/0x410 include/linux/skbuff.h:2029 __skb_try_recv_datagram+0xbe/0x220 unix_dgram_recvmsg+0xee/0x850 ____sys_recvmsg+0x1fb/0x210 ___sys_recvmsg+0xa2/0xf0 __sys_recvmsg+0x66/0xf0 __x64_sys_recvmsg+0x51/0x70 do_syscall_64+0x91/0xb47 entry_SYSCALL_64_after_hwframe+0x49/0xbe

Since only the read is operating as lockless, it could introduce a logic bug in unix_recvq_full() due to the load tearing. Fix it by adding a lockless variant of skb_queue_len() and unix_recvq_full() where READ_ONCE() is on the read while WRITE_ONCE() is on the write similar to the commit d7d16a89350a ("net: add skb_queue_empty_lockless()").

Signed-off-by: Qian Cai cai@lca.pw Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- include/linux/skbuff.h | 14 +++++++++++++- net/unix/af_unix.c | 11 +++++++++-- 2 files changed, 22 insertions(+), 3 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index cbc0294f3989..703ce71caeac 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1688,6 +1688,18 @@ static inline __u32 skb_queue_len(const struct sk_buff_head *list_) return list_->qlen; }

+/** + * skb_queue_len_lockless - get queue length + * @list_: list to measure + * + * Return the length of an &sk_buff queue. + * This variant can be used in lockless contexts. + */ +static inline __u32 skb_queue_len_lockless(const struct sk_buff_head *list_) +{ + return READ_ONCE(list_->qlen); +} + /** * __skb_queue_head_init - initialize non-spinlock portions of sk_buff_head * @list: queue to initialize @@ -1895,7 +1907,7 @@ static inline void __skb_unlink(struct sk_buff *skb, struct sk_buff_head *list) { struct sk_buff *next, *prev;

- list->qlen--; + WRITE_ONCE(list->qlen, list->qlen - 1); next = skb->next; prev = skb->prev; skb->next = skb->prev = NULL; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 2318e2e2748f..2020306468af 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -192,11 +192,17 @@ static inline int unix_may_send(struct sock *sk, struct sock *osk) return unix_peer(osk) == NULL || unix_our_peer(sk, osk); }

-static inline int unix_recvq_full(struct sock const *sk) +static inline int unix_recvq_full(const struct sock *sk) { return skb_queue_len(&sk->sk_receive_queue) > sk->sk_max_ack_backlog; }

+static inline int unix_recvq_full_lockless(const struct sock *sk) +{ + return skb_queue_len_lockless(&sk->sk_receive_queue) > + READ_ONCE(sk->sk_max_ack_backlog); +} + struct sock *unix_peer_get(struct sock *s) { struct sock *peer; @@ -1788,7 +1794,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, * - unix_peer(sk) == sk by time of get but disconnected before lock */ if (other != sk && - unlikely(unix_peer(other) != sk && unix_recvq_full(other))) { + unlikely(unix_peer(other) != sk && + unix_recvq_full_lockless(other))) { if (timeo) { timeo = unix_wait_for_peer(other, timeo);

From: Vasily Averin vvs@virtuozzo.com

[ Upstream commit 8d269a8e2a8f0bca89022f4ec98de460acb90365 ]

If seq_file .next function does not change position index, read after some lseek can generate unexpected output.

$ dd if=/sys/fs/selinux/avc/cache_stats # usual output lookups hits misses allocations reclaims frees 817223 810034 7189 7189 6992 7037 1934894 1926896 7998 7998 7632 7683 1322812 1317176 5636 5636 5456 5507 1560571 1551548 9023 9023 9056 9115 0+1 records in 0+1 records out 189 bytes copied, 5,1564e-05 s, 3,7 MB/s

$# read after lseek to midle of last line $ dd if=/sys/fs/selinux/avc/cache_stats bs=180 skip=1 dd: /sys/fs/selinux/avc/cache_stats: cannot skip to specified offset 056 9115 <<<< end of last line 1560571 1551548 9023 9023 9056 9115 <<< whole last line once again 0+1 records in 0+1 records out 45 bytes copied, 8,7221e-05 s, 516 kB/s

$# read after lseek beyond end of of file $ dd if=/sys/fs/selinux/avc/cache_stats bs=1000 skip=1 dd: /sys/fs/selinux/avc/cache_stats: cannot skip to specified offset 1560571 1551548 9023 9023 9056 9115 <<<< generates whole last line 0+1 records in 0+1 records out 36 bytes copied, 9,0934e-05 s, 396 kB/s

https://bugzilla.kernel.org/show_bug.cgi?id=206283

Signed-off-by: Vasily Averin vvs@virtuozzo.com Acked-by: Stephen Smalley sds@tycho.nsa.gov Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- security/selinux/selinuxfs.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index f3a5a138a096..60b3f16bb5c7 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -1509,6 +1509,7 @@ static struct avc_cache_stats *sel_avc_get_stat_idx(loff_t *idx) *idx = cpu + 1; return &per_cpu(avc_cache_stats, cpu); } + (*idx)++; return NULL; }

From: James Smart jsmart2021@gmail.com

[ Upstream commit 4cb9e1ddaa145be9ed67b6a7de98ca705a43f998 ]

Coverity reported a memory corruption error for the fdmi attributes routines:

CID 15768 [Memory Corruption] Out-of-bounds access on FDMI

Sloppy coding of the fmdi structures. In both the lpfc_fdmi_attr_def and lpfc_fdmi_reg_port_list structures, a field was placed at the start of payload that may have variable content. The field was given an arbitrary type (uint32_t). The code then uses the field name to derive an address, which it used in things such as memset and memcpy. The memset sizes or memcpy lengths were larger than the arbitrary type, thus coverity reported an error.

Fix by replacing the arbitrary fields with the real field structures describing the payload.

Link: https://lore.kernel.org/r/20200128002312.16346-8-jsmart2021@gmail.com Signed-off-by: Dick Kennedy dick.kennedy@broadcom.com Signed-off-by: James Smart jsmart2021@gmail.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/scsi/lpfc/lpfc_ct.c | 137 ++++++++++++++++++------------------ drivers/scsi/lpfc/lpfc_hw.h | 36 +++++----- 2 files changed, 85 insertions(+), 88 deletions(-)

diff --git a/drivers/scsi/lpfc/lpfc_ct.c b/drivers/scsi/lpfc/lpfc_ct.c index 384f5cd7c3c8..99b4ff78f9dc 100644 --- a/drivers/scsi/lpfc/lpfc_ct.c +++ b/drivers/scsi/lpfc/lpfc_ct.c @@ -1737,8 +1737,8 @@ lpfc_fdmi_hba_attr_wwnn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_def *ad) struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, sizeof(struct lpfc_name)); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

memcpy(&ae->un.AttrWWN, &vport->fc_sparam.nodeName, sizeof(struct lpfc_name)); @@ -1754,8 +1754,8 @@ lpfc_fdmi_hba_attr_manufacturer(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

/* This string MUST be consistent with other FC platforms * supported by Broadcom. @@ -1779,8 +1779,8 @@ lpfc_fdmi_hba_attr_sn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_def *ad) struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

strncpy(ae->un.AttrString, phba->SerialNumber, sizeof(ae->un.AttrString)); @@ -1801,8 +1801,8 @@ lpfc_fdmi_hba_attr_model(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

strncpy(ae->un.AttrString, phba->ModelName, sizeof(ae->un.AttrString)); @@ -1822,8 +1822,8 @@ lpfc_fdmi_hba_attr_description(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

strncpy(ae->un.AttrString, phba->ModelDesc, sizeof(ae->un.AttrString)); @@ -1845,8 +1845,8 @@ lpfc_fdmi_hba_attr_hdw_ver(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t i, j, incr, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

/* Convert JEDEC ID to ascii for hardware version */ incr = vp->rev.biuRev; @@ -1875,8 +1875,8 @@ lpfc_fdmi_hba_attr_drvr_ver(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

strncpy(ae->un.AttrString, lpfc_release_version, sizeof(ae->un.AttrString)); @@ -1897,8 +1897,8 @@ lpfc_fdmi_hba_attr_rom_ver(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

if (phba->sli_rev == LPFC_SLI_REV4) lpfc_decode_firmware_rev(phba, ae->un.AttrString, 1); @@ -1922,8 +1922,8 @@ lpfc_fdmi_hba_attr_fmw_ver(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

lpfc_decode_firmware_rev(phba, ae->un.AttrString, 1); len = strnlen(ae->un.AttrString, @@ -1942,8 +1942,8 @@ lpfc_fdmi_hba_attr_os_ver(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

snprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s %s %s", init_utsname()->sysname, @@ -1965,7 +1965,7 @@ lpfc_fdmi_hba_attr_ct_len(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;

ae->un.AttrInt = cpu_to_be32(LPFC_MAX_CT_SIZE); size = FOURBYTES + sizeof(uint32_t); @@ -1981,8 +1981,8 @@ lpfc_fdmi_hba_attr_symbolic_name(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

len = lpfc_vport_symbolic_node_name(vport, ae->un.AttrString, 256); @@ -2000,7 +2000,7 @@ lpfc_fdmi_hba_attr_vendor_info(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;

/* Nothing is defined for this currently */ ae->un.AttrInt = cpu_to_be32(0); @@ -2017,7 +2017,7 @@ lpfc_fdmi_hba_attr_num_ports(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;

/* Each driver instance corresponds to a single port */ ae->un.AttrInt = cpu_to_be32(1); @@ -2034,8 +2034,8 @@ lpfc_fdmi_hba_attr_fabric_wwnn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, sizeof(struct lpfc_name)); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

memcpy(&ae->un.AttrWWN, &vport->fabric_nodename, sizeof(struct lpfc_name)); @@ -2053,8 +2053,8 @@ lpfc_fdmi_hba_attr_bios_ver(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

lpfc_decode_firmware_rev(phba, ae->un.AttrString, 1); len = strnlen(ae->un.AttrString, @@ -2073,7 +2073,7 @@ lpfc_fdmi_hba_attr_bios_state(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;

/* Driver doesn't have access to this information */ ae->un.AttrInt = cpu_to_be32(0); @@ -2090,8 +2090,8 @@ lpfc_fdmi_hba_attr_vendor_id(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

strncpy(ae->un.AttrString, "EMULEX", sizeof(ae->un.AttrString)); @@ -2112,8 +2112,8 @@ lpfc_fdmi_port_attr_fc4type(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 32); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

ae->un.AttrTypes[3] = 0x02; /* Type 0x1 - ELS */ ae->un.AttrTypes[2] = 0x01; /* Type 0x8 - FCP */ @@ -2134,7 +2134,7 @@ lpfc_fdmi_port_attr_support_speed(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;

ae->un.AttrInt = 0; if (!(phba->hba_flag & HBA_FCOE_MODE)) { @@ -2186,7 +2186,7 @@ lpfc_fdmi_port_attr_speed(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;

if (!(phba->hba_flag & HBA_FCOE_MODE)) { switch (phba->fc_linkspeed) { @@ -2253,7 +2253,7 @@ lpfc_fdmi_port_attr_max_frame(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;

hsp = (struct serv_parm *)&vport->fc_sparam; ae->un.AttrInt = (((uint32_t) hsp->cmn.bbRcvSizeMsb) << 8) | @@ -2273,8 +2273,8 @@ lpfc_fdmi_port_attr_os_devname(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

snprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "/sys/class/scsi_host/host%d", shost->host_no); @@ -2294,8 +2294,8 @@ lpfc_fdmi_port_attr_host_name(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

snprintf(ae->un.AttrString, sizeof(ae->un.AttrString), "%s", init_utsname()->nodename); @@ -2315,8 +2315,8 @@ lpfc_fdmi_port_attr_wwnn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, sizeof(struct lpfc_name)); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

memcpy(&ae->un.AttrWWN, &vport->fc_sparam.nodeName, sizeof(struct lpfc_name)); @@ -2333,8 +2333,8 @@ lpfc_fdmi_port_attr_wwpn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, sizeof(struct lpfc_name)); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

memcpy(&ae->un.AttrWWN, &vport->fc_sparam.portName, sizeof(struct lpfc_name)); @@ -2351,8 +2351,8 @@ lpfc_fdmi_port_attr_symbolic_name(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

len = lpfc_vport_symbolic_port_name(vport, ae->un.AttrString, 256); len += (len & 3) ? (4 - (len & 3)) : 4; @@ -2370,7 +2370,7 @@ lpfc_fdmi_port_attr_port_type(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; if (phba->fc_topology == LPFC_TOPOLOGY_LOOP) ae->un.AttrInt = cpu_to_be32(LPFC_FDMI_PORTTYPE_NLPORT); else @@ -2388,7 +2388,7 @@ lpfc_fdmi_port_attr_class(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt = cpu_to_be32(FC_COS_CLASS2 | FC_COS_CLASS3); size = FOURBYTES + sizeof(uint32_t); ad->AttrLen = cpu_to_be16(size); @@ -2403,8 +2403,8 @@ lpfc_fdmi_port_attr_fabric_wwpn(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, sizeof(struct lpfc_name)); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

memcpy(&ae->un.AttrWWN, &vport->fabric_portname, sizeof(struct lpfc_name)); @@ -2421,8 +2421,8 @@ lpfc_fdmi_port_attr_active_fc4type(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 32); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

ae->un.AttrTypes[3] = 0x02; /* Type 0x1 - ELS */ ae->un.AttrTypes[2] = 0x01; /* Type 0x8 - FCP */ @@ -2442,7 +2442,7 @@ lpfc_fdmi_port_attr_port_state(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; /* Link Up - operational */ ae->un.AttrInt = cpu_to_be32(LPFC_FDMI_PORTSTATE_ONLINE); size = FOURBYTES + sizeof(uint32_t); @@ -2458,7 +2458,7 @@ lpfc_fdmi_port_attr_num_disc(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; vport->fdmi_num_disc = lpfc_find_map_node(vport); ae->un.AttrInt = cpu_to_be32(vport->fdmi_num_disc); size = FOURBYTES + sizeof(uint32_t); @@ -2474,7 +2474,7 @@ lpfc_fdmi_port_attr_nportid(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt = cpu_to_be32(vport->fc_myDID); size = FOURBYTES + sizeof(uint32_t); ad->AttrLen = cpu_to_be16(size); @@ -2489,8 +2489,8 @@ lpfc_fdmi_smart_attr_service(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

strncpy(ae->un.AttrString, "Smart SAN Initiator", sizeof(ae->un.AttrString)); @@ -2510,8 +2510,8 @@ lpfc_fdmi_smart_attr_guid(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

memcpy(&ae->un.AttrString, &vport->fc_sparam.nodeName, sizeof(struct lpfc_name)); @@ -2531,8 +2531,8 @@ lpfc_fdmi_smart_attr_version(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

strncpy(ae->un.AttrString, "Smart SAN Version 2.0", sizeof(ae->un.AttrString)); @@ -2553,8 +2553,8 @@ lpfc_fdmi_smart_attr_model(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t len, size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; - memset(ae, 0, 256); + ae = &ad->AttrValue; + memset(ae, 0, sizeof(*ae));

strncpy(ae->un.AttrString, phba->ModelName, sizeof(ae->un.AttrString)); @@ -2573,7 +2573,7 @@ lpfc_fdmi_smart_attr_port_info(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue;

/* SRIOV (type 3) is not supported */ if (vport->vpi) @@ -2593,7 +2593,7 @@ lpfc_fdmi_smart_attr_qos(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt = cpu_to_be32(0); size = FOURBYTES + sizeof(uint32_t); ad->AttrLen = cpu_to_be16(size); @@ -2608,7 +2608,7 @@ lpfc_fdmi_smart_attr_security(struct lpfc_vport *vport, struct lpfc_fdmi_attr_entry *ae; uint32_t size;

- ae = (struct lpfc_fdmi_attr_entry *)&ad->AttrValue; + ae = &ad->AttrValue; ae->un.AttrInt = cpu_to_be32(1); size = FOURBYTES + sizeof(uint32_t); ad->AttrLen = cpu_to_be16(size); @@ -2756,7 +2756,8 @@ lpfc_fdmi_cmd(struct lpfc_vport *vport, struct lpfc_nodelist *ndlp, /* Registered Port List */ /* One entry (port) per adapter */ rh->rpl.EntryCnt = cpu_to_be32(1); - memcpy(&rh->rpl.pe, &phba->pport->fc_sparam.portName, + memcpy(&rh->rpl.pe.PortName, + &phba->pport->fc_sparam.portName, sizeof(struct lpfc_name));

/* point to the HBA attribute block */ diff --git a/drivers/scsi/lpfc/lpfc_hw.h b/drivers/scsi/lpfc/lpfc_hw.h index 009aa0eee040..48d4d576d588 100644 --- a/drivers/scsi/lpfc/lpfc_hw.h +++ b/drivers/scsi/lpfc/lpfc_hw.h @@ -1333,25 +1333,8 @@ struct fc_rdp_res_frame { /* lpfc_sli_ct_request defines the CT_IU preamble for FDMI commands */ #define SLI_CT_FDMI_Subtypes 0x10 /* Management Service Subtype */

-/* - * Registered Port List Format - */ -struct lpfc_fdmi_reg_port_list { - uint32_t EntryCnt; - uint32_t pe; /* Variable-length array */ -}; - - /* Definitions for HBA / Port attribute entries */

-struct lpfc_fdmi_attr_def { /* Defined in TLV format */ - /* Structure is in Big Endian format */ - uint32_t AttrType:16; - uint32_t AttrLen:16; - uint32_t AttrValue; /* Marks start of Value (ATTRIBUTE_ENTRY) */ -}; - - /* Attribute Entry */ struct lpfc_fdmi_attr_entry { union { @@ -1362,7 +1345,13 @@ struct lpfc_fdmi_attr_entry { } un; };

-#define LPFC_FDMI_MAX_AE_SIZE sizeof(struct lpfc_fdmi_attr_entry) +struct lpfc_fdmi_attr_def { /* Defined in TLV format */ + /* Structure is in Big Endian format */ + uint32_t AttrType:16; + uint32_t AttrLen:16; + /* Marks start of Value (ATTRIBUTE_ENTRY) */ + struct lpfc_fdmi_attr_entry AttrValue; +} __packed;

/* * HBA Attribute Block @@ -1386,13 +1375,20 @@ struct lpfc_fdmi_hba_ident { struct lpfc_name PortName; };

+/* + * Registered Port List Format + */ +struct lpfc_fdmi_reg_port_list { + uint32_t EntryCnt; + struct lpfc_fdmi_port_entry pe; +} __packed; + /* * Register HBA(RHBA) */ struct lpfc_fdmi_reg_hba { struct lpfc_fdmi_hba_ident hi; - struct lpfc_fdmi_reg_port_list rpl; /* variable-length array */ -/* struct lpfc_fdmi_attr_block ab; */ + struct lpfc_fdmi_reg_port_list rpl; };

/*

From: Dinh Nguyen dinguyen@kernel.org

[ Upstream commit cc26ed7be46c5f5fa45f3df8161ed7ca3c4d318c ]

do_div() macro to perform u64 division and guards against overflow if the result is too large for the unsigned long return type.

Signed-off-by: Dinh Nguyen dinguyen@kernel.org Link: https://lkml.kernel.org/r/20200114160726.19771-1-dinguyen@kernel.org Signed-off-by: Stephen Boyd sboyd@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/clk/socfpga/clk-pll-s10.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/clk/socfpga/clk-pll-s10.c b/drivers/clk/socfpga/clk-pll-s10.c index c4d0b6f6abf2..fc2e2839fe57 100644 --- a/drivers/clk/socfpga/clk-pll-s10.c +++ b/drivers/clk/socfpga/clk-pll-s10.c @@ -38,7 +38,9 @@ static unsigned long clk_pll_recalc_rate(struct clk_hw *hwclk, /* read VCO1 reg for numerator and denominator */ reg = readl(socfpgaclk->hw.reg); refdiv = (reg & SOCFPGA_PLL_REFDIV_MASK) >> SOCFPGA_PLL_REFDIV_SHIFT; - vco_freq = (unsigned long long)parent_rate / refdiv; + + vco_freq = parent_rate; + do_div(vco_freq, refdiv);

/* Read mdiv and fdiv from the fdbck register */ reg = readl(socfpgaclk->hw.reg + 0x4);

From: Felix Fietkau nbd@nbd.name

[ Upstream commit 9379df2fd9234e3b67a23101c2370c99f6af6d77 ]

During the cleanup of the aggregation session, a rx handler (or release timer) on another CPU might still hold a pointer to the reorder buffer and could attempt to release some packets. Clearing pointers during cleanup avoids a theoretical use-after-free bug here.

Signed-off-by: Felix Fietkau nbd@nbd.name Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/net/wireless/mediatek/mt76/agg-rx.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/wireless/mediatek/mt76/agg-rx.c b/drivers/net/wireless/mediatek/mt76/agg-rx.c index d44d57e6eb27..97df6b3a472b 100644 --- a/drivers/net/wireless/mediatek/mt76/agg-rx.c +++ b/drivers/net/wireless/mediatek/mt76/agg-rx.c @@ -278,6 +278,7 @@ static void mt76_rx_aggr_shutdown(struct mt76_dev *dev, struct mt76_rx_tid *tid) if (!skb) continue;

+ tid->reorder_buf[i] = NULL; tid->nframes--; dev_kfree_skb(skb); }

From: Thomas Richter tmricht@linux.ibm.com

[ Upstream commit 2bbc83537614517730e9f2811195004b712de207 ]

This test places a kprobe to function getname_flags() in the kernel which has the following prototype:

struct filename *getname_flags(const char __user *filename, int flags, int *empty)

The 'filename' argument points to a filename located in user space memory.

Looking at commit 88903c464321c ("tracing/probe: Add ustring type for user-space string") the kprobe should indicate that user space memory is accessed.

Output before:

[root@m35lp76 perf]# ./perf test 66 67 66: Use vfs_getname probe to get syscall args filenames : FAILED! 67: Check open filename arg using perf trace + vfs_getname: FAILED! [root@m35lp76 perf]#

Output after:

[root@m35lp76 perf]# ./perf test 66 67 66: Use vfs_getname probe to get syscall args filenames : Ok 67: Check open filename arg using perf trace + vfs_getname: Ok [root@m35lp76 perf]#

Comments from Masami Hiramatsu:

This bug doesn't happen on x86 or other archs on which user address space and kernel address space is the same. On some arches (ppc64 in this case?) user address space is partially or completely the same as kernel address space.

(Yes, they switch the world when running into the kernel) In this case, we need to use different data access functions for each space.

That is why I introduced the "ustring" type for kprobe events.

As far as I can see, Thomas's patch is sane. Thomas, could you show us your result on your test environment?

Comments from Thomas Richter:

Test results for s/390 included above.

Signed-off-by: Thomas Richter tmricht@linux.ibm.com Acked-by: Masami Hiramatsu mhiramat@kernel.org Tested-by: Arnaldo Carvalho de Melo acme@redhat.com Cc: Heiko Carstens heiko.carstens@de.ibm.com Cc: Sumanth Korikkar sumanthk@linux.ibm.com Cc: Vasily Gorbik gor@linux.ibm.com Link: http://lore.kernel.org/lkml/20200217102111.61137-1-tmricht@linux.ibm.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- tools/perf/tests/shell/lib/probe_vfs_getname.sh | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh index 7cb99b433888..c2cc42daf924 100644 --- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh +++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh @@ -14,7 +14,7 @@ add_probe_vfs_getname() { if [ $had_vfs_getname -eq 1 ] ; then line=$(perf probe -L getname_flags 2>&1 | egrep 'result.*=.*filename;' | sed -r 's/[[:space:]]+([[:digit:]]+)[[:space:]]+result->uptr.*/\1/') perf probe -q "vfs_getname=getname_flags:${line} pathname=result->name:string" || \ - perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:string" + perf probe $verbose "vfs_getname=getname_flags:${line} pathname=filename:ustring" fi }

From: Paolo Bonzini pbonzini@redhat.com

[ Upstream commit 147f1a1fe5d7e6b01b8df4d0cbd6f9eaf6b6c73b ]

The "u" field in the event has three states, -1/0/1. Using u8 however means that comparison with -1 will always fail, so change to signed char.

Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- arch/x86/kvm/mmutrace.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/arch/x86/kvm/mmutrace.h b/arch/x86/kvm/mmutrace.h index cb41b036eb26..7e0dc8c7da2c 100644 --- a/arch/x86/kvm/mmutrace.h +++ b/arch/x86/kvm/mmutrace.h @@ -339,7 +339,7 @@ TRACE_EVENT( /* These depend on page entry type, so compute them now. */ __field(bool, r) __field(bool, x) - __field(u8, u) + __field(signed char, u) ),

TP_fast_assign(

From: Dan Carpenter dan.carpenter@oracle.com

[ Upstream commit ef0ed05dcef8a74178a8b480cce23a377b1de2b8 ]

There was supposed to be a "ret = " assignment here, otherwise the error handling on the next line won't work.

Fixes: 64b5a49df486 ("[media] media: imx: Add Capture Device Interface") Signed-off-by: Dan Carpenter dan.carpenter@oracle.com Reviewed-by: Steve Longerbeam slongerbeam@gmail.com Signed-off-by: Hans Verkuil hverkuil-cisco@xs4all.nl Signed-off-by: Mauro Carvalho Chehab mchehab+huawei@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/staging/media/imx/imx-media-capture.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/staging/media/imx/imx-media-capture.c b/drivers/staging/media/imx/imx-media-capture.c index 256039ce561e..81a3370551db 100644 --- a/drivers/staging/media/imx/imx-media-capture.c +++ b/drivers/staging/media/imx/imx-media-capture.c @@ -678,7 +678,7 @@ int imx_media_capture_device_register(struct imx_media_video_dev *vdev) /* setup default format */ fmt_src.pad = priv->src_sd_pad; fmt_src.which = V4L2_SUBDEV_FORMAT_ACTIVE; - v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt_src); + ret = v4l2_subdev_call(sd, pad, get_fmt, NULL, &fmt_src); if (ret) { v4l2_err(sd, "failed to get src_sd format\n"); goto unreg;

From: Thomas Gleixner tglx@linutronix.de

[ Upstream commit 8a37963c7ac9ecb7f86f8ebda020e3f8d6d7b8a0 ]

If an element is freed via RCU then recursion into BPF instrumentation functions is not a concern. The element is already detached from the map and the RCU callback does not hold any locks on which a kprobe, perf event or tracepoint attached BPF program could deadlock.

Signed-off-by: Thomas Gleixner tglx@linutronix.de Signed-off-by: Alexei Starovoitov ast@kernel.org Link: https://lore.kernel.org/bpf/20200224145643.259118710@linutronix.de Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- kernel/bpf/hashtab.c | 8 -------- 1 file changed, 8 deletions(-)

diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index 1b28fb006763..3f3ed33bd2fd 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -667,15 +667,7 @@ static void htab_elem_free_rcu(struct rcu_head *head) struct htab_elem *l = container_of(head, struct htab_elem, rcu); struct bpf_htab *htab = l->htab;

- /* must increment bpf_prog_active to avoid kprobe+bpf triggering while - * we're calling kfree, otherwise deadlock is possible if kprobes - * are placed somewhere inside of slub - */ - preempt_disable(); - __this_cpu_inc(bpf_prog_active); htab_elem_free(htab, l); - __this_cpu_dec(bpf_prog_active); - preempt_enable(); }

static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l)

From: Dmitry Osipenko digetx@gmail.com

[ Upstream commit 8e84172e372bdca20c305d92d51d33640d2da431 ]

It's incorrect to check the channel's "busy" state without taking a lock. That shouldn't cause any real troubles, nevertheless it's always better not to have any race conditions in the code.

Signed-off-by: Dmitry Osipenko digetx@gmail.com Acked-by: Jon Hunter jonathanh@nvidia.com Link: https://lore.kernel.org/r/20200209163356.6439-5-digetx@gmail.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/dma/tegra20-apb-dma.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/drivers/dma/tegra20-apb-dma.c b/drivers/dma/tegra20-apb-dma.c index 15481aeaeecd..5ccd24a46e38 100644 --- a/drivers/dma/tegra20-apb-dma.c +++ b/drivers/dma/tegra20-apb-dma.c @@ -1225,8 +1225,7 @@ static void tegra_dma_free_chan_resources(struct dma_chan *dc)

dev_dbg(tdc2dev(tdc), "Freeing channel %d\n", tdc->id);

- if (tdc->busy) - tegra_dma_terminate_all(dc); + tegra_dma_terminate_all(dc);

spin_lock_irqsave(&tdc->lock, flags); list_splice_init(&tdc->pending_sg_req, &sg_req_list);

From: James Morse james.morse@arm.com

[ Upstream commit 54f529a6806c9710947a4f2cdc15d6ea54121ccd ]

SDEI has private events that need registering and enabling on each CPU. CPUs can come and go while we are trying to do this. SDEI tries to avoid these problems by setting the reregister flag before the register call, so any CPUs that come online register the event too. Sticking plaster like this doesn't work, as if the register call fails, a CPU that subsequently comes online will register the event before reregister is cleared.

Take cpus_read_lock() around the register and enable calls. We don't want surprise CPUs to do the wrong thing if they race with these calls failing.

Signed-off-by: James Morse james.morse@arm.com Signed-off-by: Catalin Marinas catalin.marinas@arm.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/firmware/arm_sdei.c | 26 ++++++++++++++------------ 1 file changed, 14 insertions(+), 12 deletions(-)

diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c index 2b5f277819fd..14a9958377aa 100644 --- a/drivers/firmware/arm_sdei.c +++ b/drivers/firmware/arm_sdei.c @@ -433,14 +433,19 @@ int sdei_event_enable(u32 event_num) return -ENOENT; }

- spin_lock(&sdei_list_lock); - event->reenable = true; - spin_unlock(&sdei_list_lock);

+ cpus_read_lock(); if (event->type == SDEI_EVENT_TYPE_SHARED) err = sdei_api_event_enable(event->event_num); else err = sdei_do_cross_call(_local_event_enable, event); + + if (!err) { + spin_lock(&sdei_list_lock); + event->reenable = true; + spin_unlock(&sdei_list_lock); + } + cpus_read_unlock(); mutex_unlock(&sdei_events_lock);

return err; @@ -642,21 +647,18 @@ int sdei_event_register(u32 event_num, sdei_event_callback *cb, void *arg) break; }

- spin_lock(&sdei_list_lock); - event->reregister = true; - spin_unlock(&sdei_list_lock); - + cpus_read_lock(); err = _sdei_event_register(event); if (err) { - spin_lock(&sdei_list_lock); - event->reregister = false; - event->reenable = false; - spin_unlock(&sdei_list_lock); - sdei_event_destroy(event); pr_warn("Failed to register event %u: %d\n", event_num, err); + } else { + spin_lock(&sdei_list_lock); + event->reregister = true; + spin_unlock(&sdei_list_lock); } + cpus_read_unlock(); } while (0); mutex_unlock(&sdei_events_lock);

From: John Garry john.garry@huawei.com

[ Upstream commit a6dd255bdd7d00bbdbf78ba00bde9fc64f86c3a7 ]

Some released ACPI FW for Huawei boards describes incorrect the port IO address range for child devices, in that it tells us the IO port max range is 0x3fff for each child device, which is not correct. The address range should be [e4:e8) or similar. With this incorrect upper range, the child device IO port resources overlap.

As such, the kernel thinks that the LPC host serial device is a child of the IPMI device:

root@(none)$ more /proc/ioports [...] 00ffc0e3-00ffffff : hisi-lpc-ipmi.0.auto 00ffc0e3-00ffc0e3 : ipmi_si 00ffc0e4-00ffc0e4 : ipmi_si 00ffc0e5-00ffc0e5 : ipmi_si 00ffc2f7-00ffffff : serial8250.1.auto 00ffc2f7-00ffc2fe : serial root@(none)$

They should both be siblings. Note that these are logical PIO addresses, which have a direct mapping from the FW IO port ranges.

This shows up as a real issue when we enable CONFIG_KASAN and CONFIG_DEBUG_TEST_DRIVER_REMOVE - we see use-after-free warnings in the host removal path:

================================================================== BUG: KASAN: use-after-free in release_resource+0x38/0xc8 Read of size 8 at addr ffff0026accdbc38 by task swapper/0/1

CPU: 2 PID: 1 Comm: swapper/0 Not tainted 5.5.0-rc6-00001-g68e186e77b5c-dirty #1593 Hardware name: Huawei Taishan 2180 /D03, BIOS Hisilicon D03 IT20 Nemo 2.0 RC0 03/30/2018 Call trace: dump_backtrace+0x0/0x290 show_stack+0x14/0x20 dump_stack+0xf0/0x14c print_address_description.isra.9+0x6c/0x3b8 __kasan_report+0x12c/0x23c kasan_report+0xc/0x18 __asan_load8+0x94/0xb8 release_resource+0x38/0xc8 platform_device_del.part.10+0x80/0xe0 platform_device_unregister+0x20/0x38 hisi_lpc_acpi_remove_subdev+0x10/0x20 device_for_each_child+0xc8/0x128 hisi_lpc_acpi_remove+0x4c/0xa8 hisi_lpc_remove+0xbc/0xc0 platform_drv_remove+0x3c/0x68 really_probe+0x174/0x548 driver_probe_device+0x7c/0x148 device_driver_attach+0x94/0xa0 __driver_attach+0xa4/0x110 bus_for_each_dev+0xe8/0x158 driver_attach+0x30/0x40 bus_add_driver+0x234/0x2f0 driver_register+0xbc/0x1d0 __platform_driver_register+0x7c/0x88 hisi_lpc_driver_init+0x18/0x20 do_one_initcall+0xb4/0x258 kernel_init_freeable+0x248/0x2c0 kernel_init+0x10/0x118 ret_from_fork+0x10/0x1c

...

The issue here is that the kernel created an incorrect parent-child resource dependency between two devices, and references the false parent node when deleting the second child device, when it had been deleted already.

Fix up the child device resources from FW to create proper IO port resource relationships for broken FW.

With this, the IO port layout looks more healthy:

root@(none)$ more /proc/ioports [...] 00ffc0e3-00ffc0e7 : hisi-lpc-ipmi.0.auto 00ffc0e3-00ffc0e3 : ipmi_si 00ffc0e4-00ffc0e4 : ipmi_si 00ffc0e5-00ffc0e5 : ipmi_si 00ffc2f7-00ffc2ff : serial8250.1.auto 00ffc2f7-00ffc2fe : serial

Signed-off-by: John Garry john.garry@huawei.com Signed-off-by: Wei Xu xuwei5@hisilicon.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/bus/hisi_lpc.c | 27 +++++++++++++++++++++++++-- 1 file changed, 25 insertions(+), 2 deletions(-)

diff --git a/drivers/bus/hisi_lpc.c b/drivers/bus/hisi_lpc.c index 20c957185af2..2e9252d37a18 100644 --- a/drivers/bus/hisi_lpc.c +++ b/drivers/bus/hisi_lpc.c @@ -358,6 +358,26 @@ static int hisi_lpc_acpi_xlat_io_res(struct acpi_device *adev, return 0; }

+/* + * Released firmware describes the IO port max address as 0x3fff, which is + * the max host bus address. Fixup to a proper range. This will probably + * never be fixed in firmware. + */ +static void hisi_lpc_acpi_fixup_child_resource(struct device *hostdev, + struct resource *r) +{ + if (r->end != 0x3fff) + return; + + if (r->start == 0xe4) + r->end = 0xe4 + 0x04 - 1; + else if (r->start == 0x2f8) + r->end = 0x2f8 + 0x08 - 1; + else + dev_warn(hostdev, "unrecognised resource %pR to fixup, ignoring\n", + r); +} + /* * hisi_lpc_acpi_set_io_res - set the resources for a child * @child: the device node to be updated the I/O resource @@ -419,8 +439,11 @@ static int hisi_lpc_acpi_set_io_res(struct device *child, return -ENOMEM; } count = 0; - list_for_each_entry(rentry, &resource_list, node) - resources[count++] = *rentry->res; + list_for_each_entry(rentry, &resource_list, node) { + resources[count] = *rentry->res; + hisi_lpc_acpi_fixup_child_resource(hostdev, &resources[count]); + count++; + }

acpi_dev_free_resource_list(&resource_list);

From: Alain Michaud alainm@chromium.org

[ Upstream commit 08bb4da90150e2a225f35e0f642cdc463958d696 ]

Some controllers have been observed to send zero'd events under some conditions. This change guards against this condition as well as adding a trace to facilitate diagnosability of this condition.

Signed-off-by: Alain Michaud alainm@chromium.org Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- net/bluetooth/hci_event.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 2b4a7cf03041..ec6b3a87b3e7 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -5738,6 +5738,11 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) u8 status = 0, event = hdr->evt, req_evt = 0; u16 opcode = HCI_OP_NOP;

+ if (!event) { + bt_dev_warn(hdev, "Received unexpected HCI Event 00000000"); + goto done; + } + if (hdev->sent_cmd && bt_cb(hdev->sent_cmd)->hci.req_event == event) { struct hci_command_hdr *cmd_hdr = (void *) hdev->sent_cmd->data; opcode = __le16_to_cpu(cmd_hdr->opcode); @@ -5949,6 +5954,7 @@ void hci_event_packet(struct hci_dev *hdev, struct sk_buff *skb) req_complete_skb(hdev, status, opcode, orig_skb); }

+done: kfree_skb(orig_skb); kfree_skb(skb); hdev->stat.evt_rx++;

From: "Kirill A. Shutemov" kirill@shutemov.name

[ Upstream commit c3e5ea6ee574ae5e845a40ac8198de1fb63bb3ab ]

Jeff Moyer has reported that one of xfstests triggers a warning when run on DAX-enabled filesystem:

WARNING: CPU: 76 PID: 51024 at mm/memory.c:2317 wp_page_copy+0xc40/0xd50 ... wp_page_copy+0x98c/0xd50 (unreliable) do_wp_page+0xd8/0xad0 __handle_mm_fault+0x748/0x1b90 handle_mm_fault+0x120/0x1f0 __do_page_fault+0x240/0xd70 do_page_fault+0x38/0xd0 handle_page_fault+0x10/0x30

The warning happens on failed __copy_from_user_inatomic() which tries to copy data into a CoW page.

This happens because of race between MADV_DONTNEED and CoW page fault:

CPU0 CPU1 handle_mm_fault() do_wp_page() wp_page_copy() do_wp_page() madvise(MADV_DONTNEED) zap_page_range() zap_pte_range() ptep_get_and_clear_full() <TLB flush> __copy_from_user_inatomic() sees empty PTE and fails WARN_ON_ONCE(1) clear_page()

The solution is to re-try __copy_from_user_inatomic() under PTL after checking that PTE is matches the orig_pte.

The second copy attempt can still fail, like due to non-readable PTE, but there's nothing reasonable we can do about, except clearing the CoW page.

Reported-by: Jeff Moyer jmoyer@redhat.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Tested-by: Jeff Moyer jmoyer@redhat.com Cc: stable@vger.kernel.org Cc: Justin He Justin.He@arm.com Cc: Dan Williams dan.j.williams@intel.com Link: http://lkml.kernel.org/r/20200218154151.13349-1-kirill.shutemov@linux.intel.... Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- mm/memory.c | 35 +++++++++++++++++++++++++++-------- 1 file changed, 27 insertions(+), 8 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c index 6a3d5eebc951..2c5a66af85bb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2107,7 +2107,7 @@ static inline bool cow_user_page(struct page *dst, struct page *src, bool ret; void *kaddr; void __user *uaddr; - bool force_mkyoung; + bool locked = false; struct vm_area_struct *vma = vmf->vma; struct mm_struct *mm = vma->vm_mm; unsigned long addr = vmf->address; @@ -2132,11 +2132,11 @@ static inline bool cow_user_page(struct page *dst, struct page *src, * On architectures with software "accessed" bits, we would * take a double page fault, so mark it accessed here. */ - force_mkyoung = arch_faults_on_old_pte() && !pte_young(vmf->orig_pte); - if (force_mkyoung) { + if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) { pte_t entry;

vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + locked = true; if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { /* * Other thread has already handled the fault @@ -2160,18 +2160,37 @@ static inline bool cow_user_page(struct page *dst, struct page *src, * zeroes. */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { + if (locked) + goto warn; + + /* Re-validate under PTL if the page is still mapped */ + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + locked = true; + if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { + /* The PTE changed under us. Retry page fault. */ + ret = false; + goto pte_unlock; + } + /* - * Give a warn in case there can be some obscure - * use-case + * The same page can be mapped back since last copy attampt. + * Try to copy again under PTL. */ - WARN_ON_ONCE(1); - clear_page(kaddr); + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { + /* + * Give a warn in case there can be some obscure + * use-case + */ +warn: + WARN_ON_ONCE(1); + clear_page(kaddr); + } }

ret = true;

pte_unlock: - if (force_mkyoung) + if (locked) pte_unmap_unlock(vmf->pte, vmf->ptl); kunmap_atomic(kaddr); flush_dcache_page(dst);

From: Rodrigo Siqueira Rodrigo.Siqueira@amd.com

[ Upstream commit a0e40018dcc3f59a10ca21d58f8ea8ceb1b035ac ]

Raven provides retimer feature support that requires i2c interaction in order to make it work well, all settings required for this configuration are loaded from the Atom bios which include the i2c address. If the retimer feature is not available, we should abort the attempt to set this feature, otherwise, it makes the following line return I2C_CHANNEL_OPERATION_NO_RESPONSE:

i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); ... if (!i2c_success) ASSERT(i2c_success);

This ends up causing problems with hotplugging HDMI displays on Raven, and causes retimer settings to warn like so:

WARNING: CPU: 1 PID: 429 at drivers/gpu/drm/amd/amdgpu/../dal/dc/core/dc_link.c:1998 write_i2c_retimer_setting+0xc2/0x3c0 [amdgpu] Modules linked in: edac_mce_amd ccp kvm irqbypass binfmt_misc crct10dif_pclmul crc32_pclmul ghash_clmulni_intel snd_hda_codec_realtek snd_hda_codec_generic ledtrig_audio snd_hda_codec_hdmi snd_hda_intel amdgpu(+) snd_hda_codec snd_hda_core snd_hwdep snd_pcm snd_seq_midi snd_seq_midi_event snd_rawmidi aesni_intel snd_seq amd_iommu_v2 gpu_sched aes_x86_64 crypto_simd cryptd glue_helper snd_seq_device ttm drm_kms_helper snd_timer eeepc_wmi wmi_bmof asus_wmi sparse_keymap drm mxm_wmi snd k10temp fb_sys_fops syscopyarea sysfillrect sysimgblt soundcore joydev input_leds mac_hid sch_fq_codel parport_pc ppdev lp parport ip_tables x_tables autofs4 igb i2c_algo_bit hid_generic usbhid i2c_piix4 dca ahci hid libahci video wmi gpio_amdpt gpio_generic CPU: 1 PID: 429 Comm: systemd-udevd Tainted: G W 5.2.0-rc1sept162019+ #1 Hardware name: System manufacturer System Product Name/ROG STRIX B450-F GAMING, BIOS 2605 08/06/2019 RIP: 0010:write_i2c_retimer_setting+0xc2/0x3c0 [amdgpu] Code: ff 0f b6 4d ce 44 0f b6 45 cf 44 0f b6 c8 45 89 cf 44 89 e2 48 c7 c6 f0 34 bc c0 bf 04 00 00 00 e8 63 b0 90 ff 45 84 ff 75 02 <0f> 0b 42 0f b6 04 73 8d 50 f6 80 fa 02 77 8c 3c 0a 0f 85 c8 00 00 RSP: 0018:ffffa99d02726fd0 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffffa99d02727035 RCX: 0000000000000006 RDX: 0000000000000000 RSI: 0000000000000002 RDI: ffff976acc857440 RBP: ffffa99d02727018 R08: 0000000000000002 R09: 000000000002a600 R10: ffffe90610193680 R11: 00000000000005e3 R12: 000000000000005d R13: ffff976ac4b201b8 R14: 0000000000000001 R15: 0000000000000000 FS: 00007f14f99e1680(0000) GS:ffff976acc840000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fdf212843b8 CR3: 0000000408906000 CR4: 00000000003406e0 Call Trace: core_link_enable_stream+0x626/0x680 [amdgpu] dce110_apply_ctx_to_hw+0x414/0x4e0 [amdgpu] dc_commit_state+0x331/0x5e0 [amdgpu] ? drm_calc_timestamping_constants+0xf9/0x150 [drm] amdgpu_dm_atomic_commit_tail+0x395/0x1e00 [amdgpu] ? dm_plane_helper_prepare_fb+0x20c/0x280 [amdgpu] commit_tail+0x42/0x70 [drm_kms_helper] drm_atomic_helper_commit+0x10c/0x120 [drm_kms_helper] amdgpu_dm_atomic_commit+0x95/0xa0 [amdgpu] drm_atomic_commit+0x4a/0x50 [drm] restore_fbdev_mode_atomic+0x1c0/0x1e0 [drm_kms_helper] restore_fbdev_mode+0x4c/0x160 [drm_kms_helper] ? _cond_resched+0x19/0x40 drm_fb_helper_restore_fbdev_mode_unlocked+0x4e/0xa0 [drm_kms_helper] drm_fb_helper_set_par+0x2d/0x50 [drm_kms_helper] fbcon_init+0x471/0x630 visual_init+0xd5/0x130 do_bind_con_driver+0x20a/0x430 do_take_over_console+0x7d/0x1b0 do_fbcon_takeover+0x5c/0xb0 fbcon_event_notify+0x6cd/0x8a0 notifier_call_chain+0x4c/0x70 blocking_notifier_call_chain+0x43/0x60 fb_notifier_call_chain+0x1b/0x20 register_framebuffer+0x254/0x360 __drm_fb_helper_initial_config_and_unlock+0x2c5/0x510 [drm_kms_helper] drm_fb_helper_initial_config+0x35/0x40 [drm_kms_helper] amdgpu_fbdev_init+0xcd/0x100 [amdgpu] amdgpu_device_init+0x1156/0x1930 [amdgpu] amdgpu_driver_load_kms+0x8d/0x2e0 [amdgpu] drm_dev_register+0x12b/0x1c0 [drm] amdgpu_pci_probe+0xd3/0x160 [amdgpu] local_pci_probe+0x47/0xa0 pci_device_probe+0x142/0x1b0 really_probe+0xf5/0x3d0 driver_probe_device+0x11b/0x130 device_driver_attach+0x58/0x60 __driver_attach+0xa3/0x140 ? device_driver_attach+0x60/0x60 ? device_driver_attach+0x60/0x60 bus_for_each_dev+0x74/0xb0 ? kmem_cache_alloc_trace+0x1a3/0x1c0 driver_attach+0x1e/0x20 bus_add_driver+0x147/0x220 ? 0xffffffffc0cb9000 driver_register+0x60/0x100 ? 0xffffffffc0cb9000 __pci_register_driver+0x5a/0x60 amdgpu_init+0x74/0x83 [amdgpu] do_one_initcall+0x4a/0x1fa ? _cond_resched+0x19/0x40 ? kmem_cache_alloc_trace+0x3f/0x1c0 ? __vunmap+0x1cc/0x200 do_init_module+0x5f/0x227 load_module+0x2330/0x2b40 __do_sys_finit_module+0xfc/0x120 ? __do_sys_finit_module+0xfc/0x120 __x64_sys_finit_module+0x1a/0x20 do_syscall_64+0x5a/0x130 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7f14f9500839 Code: 00 f3 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 1f f6 2c 00 f7 d8 64 89 01 48 RSP: 002b:00007fff9bc4f5a8 EFLAGS: 00000246 ORIG_RAX: 0000000000000139 RAX: ffffffffffffffda RBX: 000055afb5abce30 RCX: 00007f14f9500839 RDX: 0000000000000000 RSI: 000055afb5ace0f0 RDI: 0000000000000017 RBP: 000055afb5ace0f0 R08: 0000000000000000 R09: 000000000000000a R10: 0000000000000017 R11: 0000000000000246 R12: 0000000000000000 R13: 000055afb5aad800 R14: 0000000000020000 R15: 0000000000000000 ---[ end trace c286e96563966f08 ]---

This commit reworks the way that we handle i2c write for retimer in the way that we abort this configuration if the feature is not available in the device. For debug sake, we kept a simple log message in case the retimer is not available.

Signed-off-by: Rodrigo Siqueira Rodrigo.Siqueira@amd.com Reviewed-by: Hersen Wu hersenxs.wu@amd.com Acked-by: Rodrigo Siqueira Rodrigo.Siqueira@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/gpu/drm/amd/display/dc/core/dc_link.c | 67 ++++++++----------- 1 file changed, 29 insertions(+), 38 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link.c b/drivers/gpu/drm/amd/display/dc/core/dc_link.c index 3abc0294c05f..2fb2c683ad54 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link.c @@ -1576,8 +1576,7 @@ static void write_i2c_retimer_setting( buffer, sizeof(buffer));

if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

/* Based on DP159 specs, APPLY_RX_TX_CHANGE bit in 0x0A * needs to be set to 1 on every 0xA-0xC write. @@ -1595,8 +1594,7 @@ static void write_i2c_retimer_setting( pipe_ctx->stream->sink->link->ddc, slave_address, &offset, 1, &value, 1); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; }

buffer[0] = offset; @@ -1605,8 +1603,7 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } } } @@ -1623,8 +1620,7 @@ static void write_i2c_retimer_setting( buffer, sizeof(buffer));

if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

/* Based on DP159 specs, APPLY_RX_TX_CHANGE bit in 0x0A * needs to be set to 1 on every 0xA-0xC write. @@ -1642,8 +1638,7 @@ static void write_i2c_retimer_setting( pipe_ctx->stream->sink->link->ddc, slave_address, &offset, 1, &value, 1); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; }

buffer[0] = offset; @@ -1652,8 +1647,7 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } } } @@ -1668,8 +1662,7 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

/* Write offset 0x00 to 0x23 */ buffer[0] = 0x00; @@ -1677,8 +1670,7 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

/* Write offset 0xff to 0x00 */ buffer[0] = 0xff; @@ -1686,10 +1678,14 @@ static void write_i2c_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

} + + return; + +i2c_write_fail: + DC_LOG_DEBUG("Set retimer failed"); }

static void write_i2c_default_retimer_setting( @@ -1710,8 +1706,7 @@ static void write_i2c_default_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

/* Write offset 0x0A to 0x17 */ buffer[0] = 0x0A; @@ -1719,8 +1714,7 @@ static void write_i2c_default_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

/* Write offset 0x0B to 0xDA or 0xD8 */ buffer[0] = 0x0B; @@ -1728,8 +1722,7 @@ static void write_i2c_default_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

/* Write offset 0x0A to 0x17 */ buffer[0] = 0x0A; @@ -1737,8 +1730,7 @@ static void write_i2c_default_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

/* Write offset 0x0C to 0x1D or 0x91 */ buffer[0] = 0x0C; @@ -1746,8 +1738,7 @@ static void write_i2c_default_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

/* Write offset 0x0A to 0x17 */ buffer[0] = 0x0A; @@ -1755,8 +1746,7 @@ static void write_i2c_default_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

if (is_vga_mode) { @@ -1768,8 +1758,7 @@ static void write_i2c_default_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

/* Write offset 0x00 to 0x23 */ buffer[0] = 0x00; @@ -1777,8 +1766,7 @@ static void write_i2c_default_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail;

/* Write offset 0xff to 0x00 */ buffer[0] = 0xff; @@ -1786,9 +1774,13 @@ static void write_i2c_default_retimer_setting( i2c_success = i2c_write(pipe_ctx, slave_address, buffer, sizeof(buffer)); if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + goto i2c_write_fail; } + + return; + +i2c_write_fail: + DC_LOG_DEBUG("Set default retimer failed"); }

static void write_i2c_redriver_setting( @@ -1811,8 +1803,7 @@ static void write_i2c_redriver_setting( buffer, sizeof(buffer));

if (!i2c_success) - /* Write failure */ - ASSERT(i2c_success); + DC_LOG_DEBUG("Set redriver failed"); }

static void enable_link_hdmi(struct pipe_ctx *pipe_ctx)

From: Sagar Biradar Sagar.Biradar@microchip.com

[ Upstream commit bef18d308a2215eff8c3411a23d7f34604ce56c3 ]

Fixes the occasional adapter panic when sg_reset is issued with -d, -t, -b and -H flags. Removal of command type HBA_IU_TYPE_SCSI_TM_REQ in aac_hba_send since iu_type, request_id and fib_flags are not populated. Device and target reset handlers are made to send TMF commands only when reset_state is 0.

Link: https://lore.kernel.org/r/1581553771-25796-1-git-send-email-Sagar.Biradar@mi... Reviewed-by: Sagar Biradar Sagar.Biradar@microchip.com Signed-off-by: Sagar Biradar Sagar.Biradar@microchip.com Signed-off-by: Balsundar P balsundar.p@microsemi.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/scsi/aacraid/commsup.c | 2 +- drivers/scsi/aacraid/linit.c | 34 +++++++++++++++++++++++++--------- 2 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index b7588de4484e..4cb6ee6e1212 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -743,7 +743,7 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback, hbacmd->request_id = cpu_to_le32((((u32)(fibptr - dev->fibs)) << 2) + 1); fibptr->flags |= FIB_CONTEXT_FLAG_SCSI_CMD; - } else if (command != HBA_IU_TYPE_SCSI_TM_REQ) + } else return -EINVAL;

diff --git a/drivers/scsi/aacraid/linit.c b/drivers/scsi/aacraid/linit.c index e25960e119de..49a6bfa640d0 100644 --- a/drivers/scsi/aacraid/linit.c +++ b/drivers/scsi/aacraid/linit.c @@ -737,7 +737,11 @@ static int aac_eh_abort(struct scsi_cmnd* cmd) status = aac_hba_send(HBA_IU_TYPE_SCSI_TM_REQ, fib, (fib_callback) aac_hba_callback, (void *) cmd); - + if (status != -EINPROGRESS) { + aac_fib_complete(fib); + aac_fib_free(fib); + return ret; + } /* Wait up to 15 secs for completion */ for (count = 0; count < 15; ++count) { if (cmd->SCp.sent_command) { @@ -916,11 +920,11 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd)

info = &aac->hba_map[bus][cid];

- if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && - info->reset_state > 0) + if (!(info->devtype == AAC_DEVTYPE_NATIVE_RAW && + !(info->reset_state > 0))) return FAILED;

- pr_err("%s: Host adapter reset request. SCSI hang ?\n", + pr_err("%s: Host device reset request. SCSI hang ?\n", AAC_DRIVERNAME);

fib = aac_fib_alloc(aac); @@ -935,7 +939,12 @@ static int aac_eh_dev_reset(struct scsi_cmnd *cmd) status = aac_hba_send(command, fib, (fib_callback) aac_tmf_callback, (void *) info); - + if (status != -EINPROGRESS) { + info->reset_state = 0; + aac_fib_complete(fib); + aac_fib_free(fib); + return ret; + } /* Wait up to 15 seconds for completion */ for (count = 0; count < 15; ++count) { if (info->reset_state == 0) { @@ -974,11 +983,11 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd)

info = &aac->hba_map[bus][cid];

- if (info->devtype != AAC_DEVTYPE_NATIVE_RAW && - info->reset_state > 0) + if (!(info->devtype == AAC_DEVTYPE_NATIVE_RAW && + !(info->reset_state > 0))) return FAILED;

- pr_err("%s: Host adapter reset request. SCSI hang ?\n", + pr_err("%s: Host target reset request. SCSI hang ?\n", AAC_DRIVERNAME);

fib = aac_fib_alloc(aac); @@ -995,6 +1004,13 @@ static int aac_eh_target_reset(struct scsi_cmnd *cmd) (fib_callback) aac_tmf_callback, (void *) info);

+ if (status != -EINPROGRESS) { + info->reset_state = 0; + aac_fib_complete(fib); + aac_fib_free(fib); + return ret; + } + /* Wait up to 15 seconds for completion */ for (count = 0; count < 15; ++count) { if (info->reset_state <= 0) { @@ -1047,7 +1063,7 @@ static int aac_eh_bus_reset(struct scsi_cmnd* cmd) } }

- pr_err("%s: Host adapter reset request. SCSI hang ?\n", AAC_DRIVERNAME); + pr_err("%s: Host bus reset request. SCSI hang ?\n", AAC_DRIVERNAME);

/* * Check the health of the controller

From: Colin Ian King colin.king@canonical.com

[ Upstream commit a7463e2dc698075132de9905b89f495df888bb79 ]

The shifting of buf[3] by 24 bits to the left will be promoted to a 32 bit signed int and then sign-extended to an unsigned long. In the unlikely event that the the top bit of buf[3] is set then all then all the upper bits end up as also being set because of the sign-extension and this affect the ev->post_bit_error sum. Fix this by using the temporary u32 variable bit_error to avoid the sign-extension promotion. This also removes the need to do the computation twice.

Addresses-Coverity: ("Unintended sign extension")

Fixes: 267897a4708f ("[media] tda10071: implement DVBv5 statistics") Signed-off-by: Colin Ian King colin.king@canonical.com Signed-off-by: Sean Young sean@mess.org Signed-off-by: Mauro Carvalho Chehab mchehab+huawei@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/media/dvb-frontends/tda10071.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/media/dvb-frontends/tda10071.c b/drivers/media/dvb-frontends/tda10071.c index 097c42d3f8c2..df0c7243eafe 100644 --- a/drivers/media/dvb-frontends/tda10071.c +++ b/drivers/media/dvb-frontends/tda10071.c @@ -483,10 +483,11 @@ static int tda10071_read_status(struct dvb_frontend *fe, enum fe_status *status) goto error;

if (dev->delivery_system == SYS_DVBS) { - dev->dvbv3_ber = buf[0] << 24 | buf[1] << 16 | - buf[2] << 8 | buf[3] << 0; - dev->post_bit_error += buf[0] << 24 | buf[1] << 16 | - buf[2] << 8 | buf[3] << 0; + u32 bit_error = buf[0] << 24 | buf[1] << 16 | + buf[2] << 8 | buf[3] << 0; + + dev->dvbv3_ber = bit_error; + dev->post_bit_error += bit_error; c->post_bit_error.stat[0].scale = FE_SCALE_COUNTER; c->post_bit_error.stat[0].uvalue = dev->post_bit_error; dev->block_error += buf[4] << 8 | buf[5] << 0;

From: "Darrick J. Wong" darrick.wong@oracle.com

[ Upstream commit 2e107cf869eecc770e3f630060bb4e5f547d0fd8 ]

In xchk_dir_actor, we attempt to validate the directory hash structures by performing a directory entry lookup by (hashed) name. If the lookup returns ENOENT, that means that the hash information is corrupt. The _process_error functions don't catch this, so we have to add that explicitly.

Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Reviewed-by: Dave Chinner dchinner@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/xfs/scrub/dir.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/fs/xfs/scrub/dir.c b/fs/xfs/scrub/dir.c index cd3e4d768a18..33dfcba72c7a 100644 --- a/fs/xfs/scrub/dir.c +++ b/fs/xfs/scrub/dir.c @@ -156,6 +156,9 @@ xchk_dir_actor( xname.type = XFS_DIR3_FT_UNKNOWN;

error = xfs_dir_lookup(sdc->sc->tp, ip, &xname, &lookup_ino, NULL); + /* ENOENT means the hash lookup failed and the dir is corrupt */ + if (error == -ENOENT) + error = -EFSCORRUPTED; if (!xchk_fblock_process_error(sdc->sc, XFS_DATA_FORK, offset, &error)) goto out;

From: Alexandre Belloni alexandre.belloni@bootlin.com

[ Upstream commit f2997775b111c6d660c32a18d5d44d37cb7361b1 ]

Both RTC IRQs are requested before the struct rtc_device is allocated, this may lead to a NULL pointer dereference in the IRQ handler.

To fix this issue, allocating the rtc_device struct before requesting the IRQs using devm_rtc_allocate_device, and use rtc_register_device to register the RTC device.

Link: https://lore.kernel.org/r/20200306010146.39762-1-alexandre.belloni@bootlin.c... Signed-off-by: Alexandre Belloni alexandre.belloni@bootlin.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/rtc/rtc-sa1100.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/rtc/rtc-sa1100.c b/drivers/rtc/rtc-sa1100.c index 304d905cb23f..56f625371735 100644 --- a/drivers/rtc/rtc-sa1100.c +++ b/drivers/rtc/rtc-sa1100.c @@ -186,7 +186,6 @@ static const struct rtc_class_ops sa1100_rtc_ops = {

int sa1100_rtc_init(struct platform_device *pdev, struct sa1100_rtc *info) { - struct rtc_device *rtc; int ret;

spin_lock_init(&info->lock); @@ -215,15 +214,14 @@ int sa1100_rtc_init(struct platform_device *pdev, struct sa1100_rtc *info) writel_relaxed(0, info->rcnr); }

- rtc = devm_rtc_device_register(&pdev->dev, pdev->name, &sa1100_rtc_ops, - THIS_MODULE); - if (IS_ERR(rtc)) { + info->rtc->ops = &sa1100_rtc_ops; + info->rtc->max_user_freq = RTC_FREQ; + + ret = rtc_register_device(info->rtc); + if (ret) { clk_disable_unprepare(info->clk); - return PTR_ERR(rtc); + return ret; } - info->rtc = rtc; - - rtc->max_user_freq = RTC_FREQ;

/* Fix for a nasty initialization problem the in SA11xx RTSR register. * See also the comments in sa1100_rtc_interrupt(). @@ -272,6 +270,10 @@ static int sa1100_rtc_probe(struct platform_device *pdev) info->irq_1hz = irq_1hz; info->irq_alarm = irq_alarm;

+ info->rtc = devm_rtc_allocate_device(&pdev->dev); + if (IS_ERR(info->rtc)) + return PTR_ERR(info->rtc); + ret = devm_request_irq(&pdev->dev, irq_1hz, sa1100_rtc_interrupt, 0, "rtc 1Hz", &pdev->dev); if (ret) {

From: Trond Myklebust trondmy@gmail.com

[ Upstream commit a451b12311aa8c96c6f6e01c783a86995dc3ec6b ]

In NFSv4, the lock stateids are tied to the lockowner, and the open stateid, so that the action of closing the file also results in either an automatic loss of the locks, or an error of the form NFS4ERR_LOCKS_HELD.

In practice this means we must not add new locks to the open stateid after the close process has been invoked. In fact doing so, can result in the following panic:

kernel BUG at lib/list_debug.c:51! invalid opcode: 0000 [#1] SMP NOPTI CPU: 2 PID: 1085 Comm: nfsd Not tainted 5.6.0-rc3+ #2 Hardware name: VMware, Inc. VMware7,1/440BX Desktop Reference Platform, BIOS VMW71.00V.14410784.B64.1908150010 08/15/2019 RIP: 0010:__list_del_entry_valid.cold+0x31/0x55 Code: 1a 3d 9b e8 74 10 c2 ff 0f 0b 48 c7 c7 f0 1a 3d 9b e8 66 10 c2 ff 0f 0b 48 89 f2 48 89 fe 48 c7 c7 b0 1a 3d 9b e8 52 10 c2 ff <0f> 0b 48 89 fe 4c 89 c2 48 c7 c7 78 1a 3d 9b e8 3e 10 c2 ff 0f 0b RSP: 0018:ffffb296c1d47d90 EFLAGS: 00010246 RAX: 0000000000000054 RBX: ffff8ba032456ec8 RCX: 0000000000000000 RDX: 0000000000000000 RSI: ffff8ba039e99cc8 RDI: ffff8ba039e99cc8 RBP: ffff8ba032456e60 R08: 0000000000000781 R09: 0000000000000003 R10: 0000000000000000 R11: 0000000000000001 R12: ffff8ba009a4abe0 R13: ffff8ba032456e8c R14: 0000000000000000 R15: ffff8ba00adb01d8 FS: 0000000000000000(0000) GS:ffff8ba039e80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007fb213f0b008 CR3: 00000001347de006 CR4: 00000000003606e0 Call Trace: release_lock_stateid+0x2b/0x80 [nfsd] nfsd4_free_stateid+0x1e9/0x210 [nfsd] nfsd4_proc_compound+0x414/0x700 [nfsd] ? nfs4svc_decode_compoundargs+0x407/0x4c0 [nfsd] nfsd_dispatch+0xc1/0x200 [nfsd] svc_process_common+0x476/0x6f0 [sunrpc] ? svc_sock_secure_port+0x12/0x30 [sunrpc] ? svc_recv+0x313/0x9c0 [sunrpc] ? nfsd_svc+0x2d0/0x2d0 [nfsd] svc_process+0xd4/0x110 [sunrpc] nfsd+0xe3/0x140 [nfsd] kthread+0xf9/0x130 ? nfsd_destroy+0x50/0x50 [nfsd] ? kthread_park+0x90/0x90 ret_from_fork+0x1f/0x40

The fix is to ensure that lock creation tests for whether or not the open stateid is unhashed, and to fail if that is the case.

Fixes: 659aefb68eca ("nfsd: Ensure we don't recognise lock stateids after freeing them") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/nfsd/nfs4state.c | 73 ++++++++++++++++++++++++++------------------- 1 file changed, 43 insertions(+), 30 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index c24306af9758..655079ae1dd1 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -471,6 +471,8 @@ find_any_file(struct nfs4_file *f) { struct file *ret;

+ if (!f) + return NULL; spin_lock(&f->fi_lock); ret = __nfs4_get_fd(f, O_RDWR); if (!ret) { @@ -1207,6 +1209,12 @@ static void nfs4_put_stateowner(struct nfs4_stateowner *sop) nfs4_free_stateowner(sop); }

+static bool +nfs4_ol_stateid_unhashed(const struct nfs4_ol_stateid *stp) +{ + return list_empty(&stp->st_perfile); +} + static bool unhash_ol_stateid(struct nfs4_ol_stateid *stp) { struct nfs4_file *fp = stp->st_stid.sc_file; @@ -1274,9 +1282,11 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) { lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);

+ if (!unhash_ol_stateid(stp)) + return false; list_del_init(&stp->st_locks); nfs4_unhash_stid(&stp->st_stid); - return unhash_ol_stateid(stp); + return true; }

static void release_lock_stateid(struct nfs4_ol_stateid *stp) @@ -1341,13 +1351,12 @@ static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp, static bool unhash_open_stateid(struct nfs4_ol_stateid *stp, struct list_head *reaplist) { - bool unhashed; - lockdep_assert_held(&stp->st_stid.sc_client->cl_lock);

- unhashed = unhash_ol_stateid(stp); + if (!unhash_ol_stateid(stp)) + return false; release_open_stateid_locks(stp, reaplist); - return unhashed; + return true; }

static void release_open_stateid(struct nfs4_ol_stateid *stp) @@ -5774,21 +5783,21 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, }

static struct nfs4_ol_stateid * -find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp) +find_lock_stateid(const struct nfs4_lockowner *lo, + const struct nfs4_ol_stateid *ost) { struct nfs4_ol_stateid *lst; - struct nfs4_client *clp = lo->lo_owner.so_client;

- lockdep_assert_held(&clp->cl_lock); + lockdep_assert_held(&ost->st_stid.sc_client->cl_lock);

- list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) { - if (lst->st_stid.sc_type != NFS4_LOCK_STID) - continue; - if (lst->st_stid.sc_file == fp) { - refcount_inc(&lst->st_stid.sc_count); - return lst; + /* If ost is not hashed, ost->st_locks will not be valid */ + if (!nfs4_ol_stateid_unhashed(ost)) + list_for_each_entry(lst, &ost->st_locks, st_locks) { + if (lst->st_stateowner == &lo->lo_owner) { + refcount_inc(&lst->st_stid.sc_count); + return lst; + } } - } return NULL; }

@@ -5804,11 +5813,11 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX); retry: spin_lock(&clp->cl_lock); - spin_lock(&fp->fi_lock); - retstp = find_lock_stateid(lo, fp); + if (nfs4_ol_stateid_unhashed(open_stp)) + goto out_close; + retstp = find_lock_stateid(lo, open_stp); if (retstp) - goto out_unlock; - + goto out_found; refcount_inc(&stp->st_stid.sc_count); stp->st_stid.sc_type = NFS4_LOCK_STID; stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner); @@ -5817,22 +5826,26 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; + spin_lock(&fp->fi_lock); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); list_add(&stp->st_perfile, &fp->fi_stateids); -out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&clp->cl_lock); - if (retstp) { - if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { - nfs4_put_stid(&retstp->st_stid); - goto retry; - } - /* To keep mutex tracking happy */ - mutex_unlock(&stp->st_mutex); - stp = retstp; - } return stp; +out_found: + spin_unlock(&clp->cl_lock); + if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { + nfs4_put_stid(&retstp->st_stid); + goto retry; + } + /* To keep mutex tracking happy */ + mutex_unlock(&stp->st_mutex); + return retstp; +out_close: + spin_unlock(&clp->cl_lock); + mutex_unlock(&stp->st_mutex); + return NULL; }

static struct nfs4_ol_stateid * @@ -5847,7 +5860,7 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi,

*new = false; spin_lock(&clp->cl_lock); - lst = find_lock_stateid(lo, fi); + lst = find_lock_stateid(lo, ost); spin_unlock(&clp->cl_lock); if (lst != NULL) { if (nfsd4_lock_ol_stateid(lst) == nfs_ok)

From: Gustavo Romero gromero@linux.ibm.com

[ Upstream commit 1dff3064c764b5a51c367b949b341d2e38972bec ]

On P9 DD2.2 due to a CPU defect some TM instructions need to be emulated by KVM. This is handled at first by the hardware raising a softpatch interrupt when certain TM instructions that need KVM assistance are executed in the guest. Althought some TM instructions per Power ISA are invalid forms they can raise a softpatch interrupt too. For instance, 'tresume.' instruction as defined in the ISA must have bit 31 set (1), but an instruction that matches 'tresume.' PO and XO opcode fields but has bit 31 not set (0), like 0x7cfe9ddc, also raises a softpatch interrupt. Similarly for 'treclaim.' and 'trechkpt.' instructions with bit 31 = 0, i.e. 0x7c00075c and 0x7c0007dc, respectively. Hence, if a code like the following is executed in the guest it will raise a softpatch interrupt just like a 'tresume.' when the TM facility is enabled ('tabort. 0' in the example is used only to enable the TM facility):

int main() { asm("tabort. 0; .long 0x7cfe9ddc;"); }

Currently in such a case KVM throws a complete trace like:

[345523.705984] WARNING: CPU: 24 PID: 64413 at arch/powerpc/kvm/book3s_hv_tm.c:211 kvmhv_p9_tm_emulation+0x68/0x620 [kvm_hv] [345523.705985] Modules linked in: kvm_hv(E) xt_conntrack ipt_REJECT nf_reject_ipv4 xt_tcpudp ip6table_mangle ip6table_nat iptable_mangle iptable_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 ebtable_filter ebtables ip6table_filter ip6_tables iptable_filter bridge stp llc sch_fq_codel ipmi_powernv at24 vmx_crypto ipmi_devintf ipmi_msghandler ibmpowernv uio_pdrv_genirq kvm opal_prd uio leds_powernv ib_iser rdma_cm iw_cm ib_cm ib_core iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi ip_tables x_tables autofs4 btrfs blake2b_generic zstd_compress raid10 raid456 async_raid6_recov async_memcpy async_pq async_xor async_tx libcrc32c xor raid6_pq raid1 raid0 multipath linear tg3 crct10dif_vpmsum crc32c_vpmsum ipr [last unloaded: kvm_hv] [345523.706030] CPU: 24 PID: 64413 Comm: CPU 0/KVM Tainted: G W E 5.5.0+ #1 [345523.706031] NIP: c0080000072cb9c0 LR: c0080000072b5e80 CTR: c0080000085c7850 [345523.706034] REGS: c000000399467680 TRAP: 0700 Tainted: G W E (5.5.0+) [345523.706034] MSR: 900000010282b033 <SF,HV,VEC,VSX,EE,FP,ME,IR,DR,RI,LE,TM[E]> CR: 24022428 XER: 00000000 [345523.706042] CFAR: c0080000072b5e7c IRQMASK: 0 GPR00: c0080000072b5e80 c000000399467910 c0080000072db500 c000000375ccc720 GPR04: c000000375ccc720 00000003fbec0000 0000a10395dda5a6 0000000000000000 GPR08: 000000007cfe9ddc 7cfe9ddc000005dc 7cfe9ddc7c0005dc c0080000072cd530 GPR12: c0080000085c7850 c0000003fffeb800 0000000000000001 00007dfb737f0000 GPR16: c0002001edcca558 0000000000000000 0000000000000000 0000000000000001 GPR20: c000000001b21258 c0002001edcca558 0000000000000018 0000000000000000 GPR24: 0000000001000000 ffffffffffffffff 0000000000000001 0000000000001500 GPR28: c0002001edcc4278 c00000037dd80000 800000050280f033 c000000375ccc720 [345523.706062] NIP [c0080000072cb9c0] kvmhv_p9_tm_emulation+0x68/0x620 [kvm_hv] [345523.706065] LR [c0080000072b5e80] kvmppc_handle_exit_hv.isra.53+0x3e8/0x798 [kvm_hv] [345523.706066] Call Trace: [345523.706069] [c000000399467910] [c000000399467940] 0xc000000399467940 (unreliable) [345523.706071] [c000000399467950] [c000000399467980] 0xc000000399467980 [345523.706075] [c0000003994679f0] [c0080000072bd1c4] kvmhv_run_single_vcpu+0xa1c/0xb80 [kvm_hv] [345523.706079] [c000000399467ac0] [c0080000072bd8e0] kvmppc_vcpu_run_hv+0x5b8/0xb00 [kvm_hv] [345523.706087] [c000000399467b90] [c0080000085c93cc] kvmppc_vcpu_run+0x34/0x48 [kvm] [345523.706095] [c000000399467bb0] [c0080000085c582c] kvm_arch_vcpu_ioctl_run+0x244/0x420 [kvm] [345523.706101] [c000000399467c40] [c0080000085b7498] kvm_vcpu_ioctl+0x3d0/0x7b0 [kvm] [345523.706105] [c000000399467db0] [c0000000004adf9c] ksys_ioctl+0x13c/0x170 [345523.706107] [c000000399467e00] [c0000000004adff8] sys_ioctl+0x28/0x80 [345523.706111] [c000000399467e20] [c00000000000b278] system_call+0x5c/0x68 [345523.706112] Instruction dump: [345523.706114] 419e0390 7f8a4840 409d0048 6d497c00 2f89075d 419e021c 6d497c00 2f8907dd [345523.706119] 419e01c0 6d497c00 2f8905dd 419e00a4 <0fe00000> 38210040 38600000 ebc1fff0

and then treats the executed instruction as a 'nop'.

However the POWER9 User's Manual, in section "4.6.10 Book II Invalid Forms", informs that for TM instructions bit 31 is in fact ignored, thus for the TM-related invalid forms ignoring bit 31 and handling them like the valid forms is an acceptable way to handle them. POWER8 behaves the same way too.

This commit changes the handling of the cases here described by treating the TM-related invalid forms that can generate a softpatch interrupt just like their valid forms (w/ bit 31 = 1) instead of as a 'nop' and by gently reporting any other unrecognized case to the host and treating it as illegal instruction instead of throwing a trace and treating it as a 'nop'.

Signed-off-by: Gustavo Romero gromero@linux.ibm.com Reviewed-by: Segher Boessenkool segher@kernel.crashing.org Acked-By: Michael Neuling mikey@neuling.org Reviewed-by: Leonardo Bras leonardo@linux.ibm.com Signed-off-by: Paul Mackerras paulus@ozlabs.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- arch/powerpc/include/asm/kvm_asm.h | 3 +++ arch/powerpc/kvm/book3s_hv_tm.c | 28 ++++++++++++++++++++----- arch/powerpc/kvm/book3s_hv_tm_builtin.c | 16 ++++++++++++-- 3 files changed, 40 insertions(+), 7 deletions(-)

diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h index a790d5cf6ea3..684e8ae00d16 100644 --- a/arch/powerpc/include/asm/kvm_asm.h +++ b/arch/powerpc/include/asm/kvm_asm.h @@ -163,4 +163,7 @@

#define KVM_INST_FETCH_FAILED -1

+/* Extract PO and XOP opcode fields */ +#define PO_XOP_OPCODE_MASK 0xfc0007fe + #endif /* __POWERPC_KVM_ASM_H__ */ diff --git a/arch/powerpc/kvm/book3s_hv_tm.c b/arch/powerpc/kvm/book3s_hv_tm.c index 31cd0f327c8a..e7fd60cf9780 100644 --- a/arch/powerpc/kvm/book3s_hv_tm.c +++ b/arch/powerpc/kvm/book3s_hv_tm.c @@ -6,6 +6,8 @@ * published by the Free Software Foundation. */

+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/kvm_host.h>

#include <asm/kvm_ppc.h> @@ -47,7 +49,18 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) u64 newmsr, bescr; int ra, rs;

- switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For treclaim., tsr., and trechkpt. instructions if bit + * 31 = 0 then they are per ISA invalid forms, however P9 UM, in section + * 4.6.10 Book II Invalid Forms, informs specifically that ignoring bit + * 31 is an acceptable way to handle these invalid forms that have + * bit 31 = 0. Moreover, for emulation purposes both forms (w/ and wo/ + * bit 31 set) can generate a softpatch interrupt. Hence both forms + * are handled below for these instructions so they behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -108,7 +121,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return RESUME_GUEST;

- case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* check for PR=1 and arch 2.06 bit set in PCR */ if ((msr & MSR_PR) && (vcpu->arch.vcore->pcr & PCR_ARCH_206)) { /* generate an illegal instruction interrupt */ @@ -143,7 +157,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = msr; return RESUME_GUEST;

- case PPC_INST_TRECLAIM: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECLAIM & PO_XOP_OPCODE_MASK): /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { /* generate an illegal instruction interrupt */ @@ -179,7 +194,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr &= ~MSR_TS_MASK; return RESUME_GUEST;

- case PPC_INST_TRECHKPT: + /* ignore bit 31, see comment above */ + case (PPC_INST_TRECHKPT & PO_XOP_OPCODE_MASK): /* XXX do we need to check for PR=0 here? */ /* check for TM disabled in the HFSCR or MSR */ if (!(vcpu->arch.hfscr & HFSCR_TM)) { @@ -211,6 +227,8 @@ int kvmhv_p9_tm_emulation(struct kvm_vcpu *vcpu) }

/* What should we do here? We didn't recognize the instruction */ - WARN_ON_ONCE(1); + kvmppc_core_queue_program(vcpu, SRR1_PROGILL); + pr_warn_ratelimited("Unrecognized TM-related instruction %#x for emulation", instr); + return RESUME_GUEST; } diff --git a/arch/powerpc/kvm/book3s_hv_tm_builtin.c b/arch/powerpc/kvm/book3s_hv_tm_builtin.c index 3cf5863bc06e..3c7ca2fa1959 100644 --- a/arch/powerpc/kvm/book3s_hv_tm_builtin.c +++ b/arch/powerpc/kvm/book3s_hv_tm_builtin.c @@ -26,7 +26,18 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) u64 newmsr, msr, bescr; int rs;

- switch (instr & 0xfc0007ff) { + /* + * rfid, rfebb, and mtmsrd encode bit 31 = 0 since it's a reserved bit + * in these instructions, so masking bit 31 out doesn't change these + * instructions. For the tsr. instruction if bit 31 = 0 then it is per + * ISA an invalid form, however P9 UM, in section 4.6.10 Book II Invalid + * Forms, informs specifically that ignoring bit 31 is an acceptable way + * to handle TM-related invalid forms that have bit 31 = 0. Moreover, + * for emulation purposes both forms (w/ and wo/ bit 31 set) can + * generate a softpatch interrupt. Hence both forms are handled below + * for tsr. to make them behave the same way. + */ + switch (instr & PO_XOP_OPCODE_MASK) { case PPC_INST_RFID: /* XXX do we need to check for PR=0 here? */ newmsr = vcpu->arch.shregs.srr1; @@ -76,7 +87,8 @@ int kvmhv_p9_tm_emulation_early(struct kvm_vcpu *vcpu) vcpu->arch.shregs.msr = newmsr; return 1;

- case PPC_INST_TSR: + /* ignore bit 31, see comment above */ + case (PPC_INST_TSR & PO_XOP_OPCODE_MASK): /* we know the MSR has the TS field = S (0b01) here */ msr = vcpu->arch.shregs.msr; /* check for PR=1 and arch 2.06 bit set in PCR */

From: Jordan Crouse jcrouse@codeaurora.org

[ Upstream commit 0478b4fc5f37f4d494245fe7bcce3f531cf380e9 ]

If the opp table specifies opp-supported-hw as a property but the driver has not set a supported hardware value the OPP subsystem will reject all the table entries.

Set a "default" value that will match the default table entries but not conflict with any possible real bin values. Also fix a small memory leak and free the buffer allocated by nvmem_cell_read().

Signed-off-by: Jordan Crouse jcrouse@codeaurora.org Reviewed-by: Eric Anholt eric@anholt.net Signed-off-by: Rob Clark robdclark@chromium.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 27 ++++++++++++++++++++------- 1 file changed, 20 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c index 1fc9a7fa37b4..d29a58bd2f7a 100644 --- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c +++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c @@ -1474,18 +1474,31 @@ static const struct adreno_gpu_funcs funcs = { static void check_speed_bin(struct device *dev) { struct nvmem_cell *cell; - u32 bin, val; + u32 val; + + /* + * If the OPP table specifies a opp-supported-hw property then we have + * to set something with dev_pm_opp_set_supported_hw() or the table + * doesn't get populated so pick an arbitrary value that should + * ensure the default frequencies are selected but not conflict with any + * actual bins + */ + val = 0x80;

cell = nvmem_cell_get(dev, "speed_bin");

- /* If a nvmem cell isn't defined, nothing to do */ - if (IS_ERR(cell)) - return; + if (!IS_ERR(cell)) { + void *buf = nvmem_cell_read(cell, NULL); + + if (!IS_ERR(buf)) { + u8 bin = *((u8 *) buf);

- bin = *((u32 *) nvmem_cell_read(cell, NULL)); - nvmem_cell_put(cell); + val = (1 << bin); + kfree(buf); + }

- val = (1 << bin); + nvmem_cell_put(cell); + }

dev_pm_opp_set_supported_hw(dev, &val, 1); }

From: Niklas Söderlund niklas.soderlund+renesas@ragnatech.se

[ Upstream commit 39056e8a989ef52486e063e34b4822b341e47b0e ]

If the common register memory resource is not available the driver needs to fail gracefully to disable PM. Instead of returning the error directly store it in ret and use the already existing error path.

Signed-off-by: Niklas Söderlund niklas.soderlund+renesas@ragnatech.se Reviewed-by: Geert Uytterhoeven geert+renesas@glider.be Signed-off-by: Daniel Lezcano daniel.lezcano@linaro.org Link: https://lore.kernel.org/r/20200310114709.1483860-1-niklas.soderlund+renesas@... Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/thermal/rcar_thermal.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/thermal/rcar_thermal.c b/drivers/thermal/rcar_thermal.c index 4dc30e7890f6..140386d7c75a 100644 --- a/drivers/thermal/rcar_thermal.c +++ b/drivers/thermal/rcar_thermal.c @@ -505,8 +505,10 @@ static int rcar_thermal_probe(struct platform_device *pdev) res = platform_get_resource(pdev, IORESOURCE_MEM, mres++); common->base = devm_ioremap_resource(dev, res); - if (IS_ERR(common->base)) - return PTR_ERR(common->base); + if (IS_ERR(common->base)) { + ret = PTR_ERR(common->base); + goto error_unregister; + }

idle = 0; /* polling delay is not needed */ }

From: Vignesh Raghavendra vigneshr@ti.com

[ Upstream commit f19c3f6c8109b8bab000afd35580929958e087a9 ]

When port's throttle callback is called, it should stop pushing any more data into TTY buffer to avoid buffer overflow. This means driver has to stop HW from receiving more data and assert the HW flow control. For UARTs with auto HW flow control (such as 8250_omap) manual assertion of flow control line is not possible and only way is to allow RX FIFO to fill up, thus trigger auto HW flow control logic.

Therefore make sure that 8250 generic IRQ handler does not drain data when port is stopped (i.e UART_LSR_DR is unset in read_status_mask). Not servicing, RX FIFO would trigger auto HW flow control when FIFO occupancy reaches preset threshold, thus halting RX. Since, error conditions in UART_LSR register are cleared just by reading the register, data has to be drained in case there are FIFO errors, else error information will lost.

Signed-off-by: Vignesh Raghavendra vigneshr@ti.com Link: https://lore.kernel.org/r/20200319103230.16867-2-vigneshr@ti.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/tty/serial/8250/8250_port.c | 16 +++++++++++++++- 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 09f0dc3b967b..60ca19eca1f6 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1861,6 +1861,7 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) unsigned char status; unsigned long flags; struct uart_8250_port *up = up_to_u8250p(port); + bool skip_rx = false;

if (iir & UART_IIR_NO_INT) return 0; @@ -1869,7 +1870,20 @@ int serial8250_handle_irq(struct uart_port *port, unsigned int iir)

status = serial_port_in(port, UART_LSR);

- if (status & (UART_LSR_DR | UART_LSR_BI)) { + /* + * If port is stopped and there are no error conditions in the + * FIFO, then don't drain the FIFO, as this may lead to TTY buffer + * overflow. Not servicing, RX FIFO would trigger auto HW flow + * control when FIFO occupancy reaches preset threshold, thus + * halting RX. This only works when auto HW flow control is + * available. + */ + if (!(status & (UART_LSR_FIFOE | UART_LSR_BRK_ERROR_BITS)) && + (port->status & (UPSTAT_AUTOCTS | UPSTAT_AUTORTS)) && + !(port->read_status_mask & UART_LSR_DR)) + skip_rx = true; + + if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) { if (!up->dma || handle_rx_dma(up, iir)) status = serial8250_rx_chars(up, status); }

From: Vignesh Raghavendra vigneshr@ti.com

[ Upstream commit 7cf4df30a98175033e9849f7f16c46e96ba47f41 ]

Terminate and flush DMA internal buffers, before pushing RX data to higher layer. Otherwise, this will lead to data corruption, as driver would end up pushing stale buffer data to higher layer while actual data is still stuck inside DMA hardware and has yet not arrived at the memory. While at that, replace deprecated dmaengine_terminate_all() with dmaengine_terminate_async().

Signed-off-by: Vignesh Raghavendra vigneshr@ti.com Link: https://lore.kernel.org/r/20200319110344.21348-2-vigneshr@ti.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/tty/serial/8250/8250_omap.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index a7e555e413a6..cbd006fb7fbb 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -781,7 +781,10 @@ static void __dma_rx_do_complete(struct uart_8250_port *p) dmaengine_tx_status(dma->rxchan, dma->rx_cookie, &state);

count = dma->rx_size - state.residue; - + if (count < dma->rx_size) + dmaengine_terminate_async(dma->rxchan); + if (!count) + goto unlock; ret = tty_insert_flip_string(tty_port, dma->rx_buf, count);

p->port.icount.rx += ret; @@ -843,7 +846,6 @@ static void omap_8250_rx_dma_flush(struct uart_8250_port *p) spin_unlock_irqrestore(&priv->rx_dma_lock, flags);

__dma_rx_do_complete(p); - dmaengine_terminate_all(dma->rxchan); }

static int omap_8250_rx_dma(struct uart_8250_port *p)

From: Pratik Rajesh Sampat psampat@linux.ibm.com

[ Upstream commit d95fe371ecd28901f11256c610b988ed44e36ee2 ]

The patch avoids allocating cpufreq_policy on stack hence fixing frame size overflow in 'powernv_cpufreq_work_fn'

Fixes: 227942809b52 ("cpufreq: powernv: Restore cpu frequency to policy->cur on unthrottling") Signed-off-by: Pratik Rajesh Sampat psampat@linux.ibm.com Reviewed-by: Daniel Axtens dja@axtens.net Signed-off-by: Michael Ellerman mpe@ellerman.id.au Link: https://lore.kernel.org/r/20200316135743.57735-1-psampat@linux.ibm.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/cpufreq/powernv-cpufreq.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-)

diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index 687c92ef7644..79942f705757 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -903,6 +903,7 @@ static struct notifier_block powernv_cpufreq_reboot_nb = { void powernv_cpufreq_work_fn(struct work_struct *work) { struct chip *chip = container_of(work, struct chip, throttle); + struct cpufreq_policy *policy; unsigned int cpu; cpumask_t mask;

@@ -917,12 +918,14 @@ void powernv_cpufreq_work_fn(struct work_struct *work) chip->restore = false; for_each_cpu(cpu, &mask) { int index; - struct cpufreq_policy policy;

- cpufreq_get_policy(&policy, cpu); - index = cpufreq_table_find_index_c(&policy, policy.cur); - powernv_cpufreq_target_index(&policy, index); - cpumask_andnot(&mask, &mask, policy.cpus); + policy = cpufreq_cpu_get(cpu); + if (!policy) + continue; + index = cpufreq_table_find_index_c(policy, policy->cur); + powernv_cpufreq_target_index(policy, index); + cpumask_andnot(&mask, &mask, policy->cpus); + cpufreq_cpu_put(policy); } out: put_online_cpus();

From: John Meneghini johnm@netapp.com

[ Upstream commit 764e9332098c0e60251386a507fe46ac91276120 ]

The nvme multipath error handling defaults to controller reset if the error is unknown. There are, however, no existing nvme status codes that indicate a reset should be used, and resetting causes unnecessary disruption to the rest of IO.

Change nvme's error handling to first check if failover should happen. If not, let the normal error handling take over rather than reset the controller.

Based-on-a-patch-by: Christoph Hellwig hch@lst.de Reviewed-by: Hannes Reinecke hare@suse.de Signed-off-by: John Meneghini johnm@netapp.com Signed-off-by: Keith Busch kbusch@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/nvme/host/core.c | 5 +---- drivers/nvme/host/multipath.c | 21 +++++++++------------ drivers/nvme/host/nvme.h | 5 +++-- 3 files changed, 13 insertions(+), 18 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 5c88aabf7dfe..7080c030d038 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -261,11 +261,8 @@ void nvme_complete_rq(struct request *req) trace_nvme_complete_rq(req);

if (unlikely(status != BLK_STS_OK && nvme_req_needs_retry(req))) { - if ((req->cmd_flags & REQ_NVME_MPATH) && - blk_path_error(status)) { - nvme_failover_req(req); + if ((req->cmd_flags & REQ_NVME_MPATH) && nvme_failover_req(req)) return; - }

if (!blk_queue_dying(req->q)) { nvme_req(req)->retries++; diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 2e63c1106030..e71075338ff5 100644 --- a/drivers/nvme/host/multipath.c +++ b/drivers/nvme/host/multipath.c @@ -73,17 +73,12 @@ void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, } }

-void nvme_failover_req(struct request *req) +bool nvme_failover_req(struct request *req) { struct nvme_ns *ns = req->q->queuedata; u16 status = nvme_req(req)->status; unsigned long flags;

- spin_lock_irqsave(&ns->head->requeue_lock, flags); - blk_steal_bios(&ns->head->requeue_list, req); - spin_unlock_irqrestore(&ns->head->requeue_lock, flags); - blk_mq_end_request(req, 0); - switch (status & 0x7ff) { case NVME_SC_ANA_TRANSITION: case NVME_SC_ANA_INACCESSIBLE: @@ -111,15 +106,17 @@ void nvme_failover_req(struct request *req) nvme_mpath_clear_current_path(ns); break; default: - /* - * Reset the controller for any non-ANA error as we don't know - * what caused the error. - */ - nvme_reset_ctrl(ns->ctrl); - break; + /* This was a non-ANA error so follow the normal error path. */ + return false; }

+ spin_lock_irqsave(&ns->head->requeue_lock, flags); + blk_steal_bios(&ns->head->requeue_list, req); + spin_unlock_irqrestore(&ns->head->requeue_lock, flags); + blk_mq_end_request(req, 0); + kblockd_schedule_work(&ns->head->requeue_work); + return true; }

void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h index cc4273f11989..31c1496f938f 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -477,7 +477,7 @@ void nvme_mpath_wait_freeze(struct nvme_subsystem *subsys); void nvme_mpath_start_freeze(struct nvme_subsystem *subsys); void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, struct nvme_ctrl *ctrl, int *flags); -void nvme_failover_req(struct request *req); +bool nvme_failover_req(struct request *req); void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl); int nvme_mpath_alloc_disk(struct nvme_ctrl *ctrl,struct nvme_ns_head *head); void nvme_mpath_add_disk(struct nvme_ns *ns, struct nvme_id_ns *id); @@ -521,8 +521,9 @@ static inline void nvme_set_disk_name(char *disk_name, struct nvme_ns *ns, sprintf(disk_name, "nvme%dn%d", ctrl->instance, ns->head->instance); }

-static inline void nvme_failover_req(struct request *req) +static inline bool nvme_failover_req(struct request *req) { + return false; } static inline void nvme_kick_requeue_lists(struct nvme_ctrl *ctrl) {

From: Zhu Yanjun yanjunz@mellanox.com

[ Upstream commit d0ca2c35dd15a3d989955caec02beea02f735ee6 ]

The RXE driver doesn't set sys_image_guid and user space applications see zeros. This causes to pyverbs tests to fail with the following traceback, because the IBTA spec requires to have valid sys_image_guid.

Traceback (most recent call last): File "./tests/test_device.py", line 51, in test_query_device self.verify_device_attr(attr) File "./tests/test_device.py", line 74, in verify_device_attr assert attr.sys_image_guid != 0

In order to fix it, set sys_image_guid to be equal to node_guid.

Before: 5: rxe0: ... node_guid 5054:00ff:feaa:5363 sys_image_guid 0000:0000:0000:0000

After: 5: rxe0: ... node_guid 5054:00ff:feaa:5363 sys_image_guid 5054:00ff:feaa:5363

Fixes: 8700e3e7c485 ("Soft RoCE driver") Link: https://lore.kernel.org/r/20200323112800.1444784-1-leon@kernel.org Signed-off-by: Zhu Yanjun yanjunz@mellanox.com Signed-off-by: Leon Romanovsky leonro@mellanox.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/infiniband/sw/rxe/rxe.c | 2 ++ 1 file changed, 2 insertions(+)

diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c index 94dedabe648c..6589ff51eaf5 100644 --- a/drivers/infiniband/sw/rxe/rxe.c +++ b/drivers/infiniband/sw/rxe/rxe.c @@ -121,6 +121,8 @@ static void rxe_init_device_param(struct rxe_dev *rxe) rxe->attr.max_fast_reg_page_list_len = RXE_MAX_FMR_PAGE_LIST_LEN; rxe->attr.max_pkeys = RXE_MAX_PKEYS; rxe->attr.local_ca_ack_delay = RXE_LOCAL_CA_ACK_DELAY; + addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid, + rxe->ndev->dev_addr);

rxe->max_ucontext = RXE_MAX_UCONTEXT; }

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit b25b60d7bfb02a74bc3c2d998e09aab159df8059 ]

'maxlen' is the total size of the destination buffer. There is only one caller and this value is 256.

When we compute the size already used and what we would like to add in the buffer, the trailling NULL character is not taken into account. However, this trailling character will be added by the 'strcat' once we have checked that we have enough place.

So, there is a off-by-one issue and 1 byte of the stack could be erroneously overwridden.

Take into account the trailling NULL, when checking if there is enough place in the destination buffer.

While at it, also replace a 'sprintf' by a safer 'snprintf', check for output truncation and avoid a superfluous 'strlen'.

Fixes: dc9a16e49dbba ("svc: Add /proc/sys/sunrpc/transport files") Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr [ cel: very minor fix to documenting comment Signed-off-by: Chuck Lever chuck.lever@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- net/sunrpc/svc_xprt.c | 19 ++++++++++++++----- 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index cf9ab055b1c2..2c8c3193dca7 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -103,8 +103,17 @@ void svc_unreg_xprt_class(struct svc_xprt_class *xcl) } EXPORT_SYMBOL_GPL(svc_unreg_xprt_class);

-/* - * Format the transport list for printing +/** + * svc_print_xprts - Format the transport list for printing + * @buf: target buffer for formatted address + * @maxlen: length of target buffer + * + * Fills in @buf with a string containing a list of transport names, each name + * terminated with '\n'. If the buffer is too small, some entries may be + * missing, but it is guaranteed that all lines in the output buffer are + * complete. + * + * Returns positive length of the filled-in string. */ int svc_print_xprts(char *buf, int maxlen) { @@ -117,9 +126,9 @@ int svc_print_xprts(char *buf, int maxlen) list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) { int slen;

- sprintf(tmpstr, "%s %d\n", xcl->xcl_name, xcl->xcl_max_payload); - slen = strlen(tmpstr); - if (len + slen > maxlen) + slen = snprintf(tmpstr, sizeof(tmpstr), "%s %d\n", + xcl->xcl_name, xcl->xcl_max_payload); + if (slen >= sizeof(tmpstr) || len + slen >= maxlen) break; len += slen; strcat(buf, tmpstr);

From: Mikel Rychliski mikel@mikelr.com

[ Upstream commit 72e0ef0e5f067fd991f702f0b2635d911d0cf208 ]

On some EFI systems, the video BIOS is provided by the EFI firmware. The boot stub code stores the physical address of the ROM image in pdev->rom. Currently we attempt to access this pointer using phys_to_virt(), which doesn't work with CONFIG_HIGHMEM.

On these systems, attempting to load the radeon module on a x86_32 kernel can result in the following:

BUG: unable to handle page fault for address: 3e8ed03c #PF: supervisor read access in kernel mode #PF: error_code(0x0000) - not-present page *pde = 00000000 Oops: 0000 [#1] PREEMPT SMP CPU: 0 PID: 317 Comm: systemd-udevd Not tainted 5.6.0-rc3-next-20200228 #2 Hardware name: Apple Computer, Inc. MacPro1,1/Mac-F4208DC8, BIOS MP11.88Z.005C.B08.0707021221 07/02/07 EIP: radeon_get_bios+0x5ed/0xe50 [radeon] Code: 00 00 84 c0 0f 85 12 fd ff ff c7 87 64 01 00 00 00 00 00 00 8b 47 08 8b 55 b0 e8 1e 83 e1 d6 85 c0 74 1a 8b 55 c0 85 d2 74 13 <80> 38 55 75 0e 80 78 01 aa 0f 84 a4 03 00 00 8d 74 26 00 68 dc 06 EAX: 3e8ed03c EBX: 00000000 ECX: 3e8ed03c EDX: 00010000 ESI: 00040000 EDI: eec04000 EBP: eef3fc60 ESP: eef3fbe0 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 EFLAGS: 00010206 CR0: 80050033 CR2: 3e8ed03c CR3: 2ec77000 CR4: 000006d0 Call Trace: r520_init+0x26/0x240 [radeon] radeon_device_init+0x533/0xa50 [radeon] radeon_driver_load_kms+0x80/0x220 [radeon] drm_dev_register+0xa7/0x180 [drm] radeon_pci_probe+0x10f/0x1a0 [radeon] pci_device_probe+0xd4/0x140

Fix the issue by updating all drivers which can access a platform provided ROM. Instead of calling the helper function pci_platform_rom() which uses phys_to_virt(), call ioremap() directly on the pdev->rom.

radeon_read_platform_bios() previously directly accessed an __iomem pointer. Avoid this by calling memcpy_fromio() instead of kmemdup().

pci_platform_rom() now has no remaining callers, so remove it.

Link: https://lore.kernel.org/r/20200319021623.5426-1-mikel@mikelr.com Signed-off-by: Mikel Rychliski mikel@mikelr.com Signed-off-by: Bjorn Helgaas bhelgaas@google.com Acked-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c | 31 +++++++++++-------- .../drm/nouveau/nvkm/subdev/bios/shadowpci.c | 17 ++++++++-- drivers/gpu/drm/radeon/radeon_bios.c | 30 +++++++++++------- drivers/pci/rom.c | 17 ---------- include/linux/pci.h | 1 - 5 files changed, 52 insertions(+), 44 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c index a5df80d50d44..6cf3dd5edffd 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_bios.c @@ -191,30 +191,35 @@ static bool amdgpu_read_bios_from_rom(struct amdgpu_device *adev)

static bool amdgpu_read_platform_bios(struct amdgpu_device *adev) { - uint8_t __iomem *bios; - size_t size; + phys_addr_t rom = adev->pdev->rom; + size_t romlen = adev->pdev->romlen; + void __iomem *bios;

adev->bios = NULL;

- bios = pci_platform_rom(adev->pdev, &size); - if (!bios) { + if (!rom || romlen == 0) return false; - }

- adev->bios = kzalloc(size, GFP_KERNEL); - if (adev->bios == NULL) + adev->bios = kzalloc(romlen, GFP_KERNEL); + if (!adev->bios) return false;

- memcpy_fromio(adev->bios, bios, size); + bios = ioremap(rom, romlen); + if (!bios) + goto free_bios;

- if (!check_atom_bios(adev->bios, size)) { - kfree(adev->bios); - return false; - } + memcpy_fromio(adev->bios, bios, romlen); + iounmap(bios);

- adev->bios_size = size; + if (!check_atom_bios(adev->bios, romlen)) + goto free_bios; + + adev->bios_size = romlen;

return true; +free_bios: + kfree(adev->bios); + return false; }

#ifdef CONFIG_ACPI diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c index 9b91da09dc5f..8d9812a51ef6 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/shadowpci.c @@ -101,9 +101,13 @@ platform_init(struct nvkm_bios *bios, const char *name) else return ERR_PTR(-ENODEV);

+ if (!pdev->rom || pdev->romlen == 0) + return ERR_PTR(-ENODEV); + if ((priv = kmalloc(sizeof(*priv), GFP_KERNEL))) { + priv->size = pdev->romlen; if (ret = -ENODEV, - (priv->rom = pci_platform_rom(pdev, &priv->size))) + (priv->rom = ioremap(pdev->rom, pdev->romlen))) return priv; kfree(priv); } @@ -111,11 +115,20 @@ platform_init(struct nvkm_bios *bios, const char *name) return ERR_PTR(ret); }

+static void +platform_fini(void *data) +{ + struct priv *priv = data; + + iounmap(priv->rom); + kfree(priv); +} + const struct nvbios_source nvbios_platform = { .name = "PLATFORM", .init = platform_init, - .fini = (void(*)(void *))kfree, + .fini = platform_fini, .read = pcirom_read, .rw = true, }; diff --git a/drivers/gpu/drm/radeon/radeon_bios.c b/drivers/gpu/drm/radeon/radeon_bios.c index 04c0ed41374f..dd0528cf9818 100644 --- a/drivers/gpu/drm/radeon/radeon_bios.c +++ b/drivers/gpu/drm/radeon/radeon_bios.c @@ -104,25 +104,33 @@ static bool radeon_read_bios(struct radeon_device *rdev)

static bool radeon_read_platform_bios(struct radeon_device *rdev) { - uint8_t __iomem *bios; - size_t size; + phys_addr_t rom = rdev->pdev->rom; + size_t romlen = rdev->pdev->romlen; + void __iomem *bios;

rdev->bios = NULL;

- bios = pci_platform_rom(rdev->pdev, &size); - if (!bios) { + if (!rom || romlen == 0) return false; - }

- if (size == 0 || bios[0] != 0x55 || bios[1] != 0xaa) { + rdev->bios = kzalloc(romlen, GFP_KERNEL); + if (!rdev->bios) return false; - } - rdev->bios = kmemdup(bios, size, GFP_KERNEL); - if (rdev->bios == NULL) { - return false; - } + + bios = ioremap(rom, romlen); + if (!bios) + goto free_bios; + + memcpy_fromio(rdev->bios, bios, romlen); + iounmap(bios); + + if (rdev->bios[0] != 0x55 || rdev->bios[1] != 0xaa) + goto free_bios;

return true; +free_bios: + kfree(rdev->bios); + return false; }

#ifdef CONFIG_ACPI diff --git a/drivers/pci/rom.c b/drivers/pci/rom.c index 137bf0cee897..8fc9a4e911e3 100644 --- a/drivers/pci/rom.c +++ b/drivers/pci/rom.c @@ -195,20 +195,3 @@ void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom) pci_disable_rom(pdev); } EXPORT_SYMBOL(pci_unmap_rom); - -/** - * pci_platform_rom - provides a pointer to any ROM image provided by the - * platform - * @pdev: pointer to pci device struct - * @size: pointer to receive size of pci window over ROM - */ -void __iomem *pci_platform_rom(struct pci_dev *pdev, size_t *size) -{ - if (pdev->rom && pdev->romlen) { - *size = pdev->romlen; - return phys_to_virt((phys_addr_t)pdev->rom); - } - - return NULL; -} -EXPORT_SYMBOL(pci_platform_rom); diff --git a/include/linux/pci.h b/include/linux/pci.h index c97de5c8bc35..97ced71acadd 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1189,7 +1189,6 @@ int pci_enable_rom(struct pci_dev *pdev); void pci_disable_rom(struct pci_dev *pdev); void __iomem __must_check *pci_map_rom(struct pci_dev *pdev, size_t *size); void pci_unmap_rom(struct pci_dev *pdev, void __iomem *rom); -void __iomem __must_check *pci_platform_rom(struct pci_dev *pdev, size_t *size);

/* Power management related routines */ int pci_save_state(struct pci_dev *dev);

From: Andreas Steinmetz ast@domdv.de

[ Upstream commit 5c6cd7021a05a02fcf37f360592d7c18d4d807fb ]

The Miditech MIDIFACE 16x16 (USB ID 1290:1749) has more than one extra endpoint descriptor.

The first extra descriptor is: 0x06 0x30 0x00 0x00 0x00 0x00

As the code in snd_usbmidi_get_ms_info() looks only at the first extra descriptor to find USB_DT_CS_ENDPOINT the device as such is recognized but there is neither input nor output configured.

The patch iterates through the extra descriptors to find the proper one. With this patch the device is correctly configured.

Signed-off-by: Andreas Steinmetz ast@domdv.de Link: https://lore.kernel.org/r/1c3b431a86f69e1d60745b6110cdb93c299f120b.camel@dom... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- sound/usb/midi.c | 29 ++++++++++++++++++++++++----- 1 file changed, 24 insertions(+), 5 deletions(-)

diff --git a/sound/usb/midi.c b/sound/usb/midi.c index 28a3ad8b1d74..137e1e8718d6 100644 --- a/sound/usb/midi.c +++ b/sound/usb/midi.c @@ -1828,6 +1828,28 @@ static int snd_usbmidi_create_endpoints(struct snd_usb_midi *umidi, return 0; }

+static struct usb_ms_endpoint_descriptor *find_usb_ms_endpoint_descriptor( + struct usb_host_endpoint *hostep) +{ + unsigned char *extra = hostep->extra; + int extralen = hostep->extralen; + + while (extralen > 3) { + struct usb_ms_endpoint_descriptor *ms_ep = + (struct usb_ms_endpoint_descriptor *)extra; + + if (ms_ep->bLength > 3 && + ms_ep->bDescriptorType == USB_DT_CS_ENDPOINT && + ms_ep->bDescriptorSubtype == UAC_MS_GENERAL) + return ms_ep; + if (!extra[0]) + break; + extralen -= extra[0]; + extra += extra[0]; + } + return NULL; +} + /* * Returns MIDIStreaming device capabilities. */ @@ -1865,11 +1887,8 @@ static int snd_usbmidi_get_ms_info(struct snd_usb_midi *umidi, ep = get_ep_desc(hostep); if (!usb_endpoint_xfer_bulk(ep) && !usb_endpoint_xfer_int(ep)) continue; - ms_ep = (struct usb_ms_endpoint_descriptor *)hostep->extra; - if (hostep->extralen < 4 || - ms_ep->bLength < 4 || - ms_ep->bDescriptorType != USB_DT_CS_ENDPOINT || - ms_ep->bDescriptorSubtype != UAC_MS_GENERAL) + ms_ep = find_usb_ms_endpoint_descriptor(hostep); + if (!ms_ep) continue; if (usb_endpoint_dir_out(ep)) { if (endpoints[epidx].out_ep) {

From: Trond Myklebust trond.myklebust@hammerspace.com

[ Upstream commit 08ca8b21f760c0ed5034a5c122092eec22ccf8f4 ]

When a subrequest is being detached from the subgroup, we want to ensure that it is not holding the group lock, or in the process of waiting for the group lock.

Fixes: 5b2b5187fa85 ("NFS: Fix nfs_page_group_destroy() and nfs_lock_and_join_requests() race cases") Signed-off-by: Trond Myklebust trond.myklebust@hammerspace.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/nfs/pagelist.c | 67 +++++++++++++++++++++++++++------------- fs/nfs/write.c | 10 ++++-- include/linux/nfs_page.h | 2 ++ 3 files changed, 55 insertions(+), 24 deletions(-)

diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 5dae7c85d9b6..2c7d76b4c5e1 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -132,47 +132,70 @@ nfs_async_iocounter_wait(struct rpc_task *task, struct nfs_lock_context *l_ctx) EXPORT_SYMBOL_GPL(nfs_async_iocounter_wait);

/* - * nfs_page_group_lock - lock the head of the page group - * @req - request in group that is to be locked + * nfs_page_set_headlock - set the request PG_HEADLOCK + * @req: request that is to be locked * - * this lock must be held when traversing or modifying the page - * group list + * this lock must be held when modifying req->wb_head * * return 0 on success, < 0 on error */ int -nfs_page_group_lock(struct nfs_page *req) +nfs_page_set_headlock(struct nfs_page *req) { - struct nfs_page *head = req->wb_head; - - WARN_ON_ONCE(head != head->wb_head); - - if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags)) + if (!test_and_set_bit(PG_HEADLOCK, &req->wb_flags)) return 0;

- set_bit(PG_CONTENDED1, &head->wb_flags); + set_bit(PG_CONTENDED1, &req->wb_flags); smp_mb__after_atomic(); - return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK, + return wait_on_bit_lock(&req->wb_flags, PG_HEADLOCK, TASK_UNINTERRUPTIBLE); }

/* - * nfs_page_group_unlock - unlock the head of the page group - * @req - request in group that is to be unlocked + * nfs_page_clear_headlock - clear the request PG_HEADLOCK + * @req: request that is to be locked */ void -nfs_page_group_unlock(struct nfs_page *req) +nfs_page_clear_headlock(struct nfs_page *req) { - struct nfs_page *head = req->wb_head; - - WARN_ON_ONCE(head != head->wb_head); - smp_mb__before_atomic(); - clear_bit(PG_HEADLOCK, &head->wb_flags); + clear_bit(PG_HEADLOCK, &req->wb_flags); smp_mb__after_atomic(); - if (!test_bit(PG_CONTENDED1, &head->wb_flags)) + if (!test_bit(PG_CONTENDED1, &req->wb_flags)) return; - wake_up_bit(&head->wb_flags, PG_HEADLOCK); + wake_up_bit(&req->wb_flags, PG_HEADLOCK); +} + +/* + * nfs_page_group_lock - lock the head of the page group + * @req: request in group that is to be locked + * + * this lock must be held when traversing or modifying the page + * group list + * + * return 0 on success, < 0 on error + */ +int +nfs_page_group_lock(struct nfs_page *req) +{ + int ret; + + ret = nfs_page_set_headlock(req); + if (ret || req->wb_head == req) + return ret; + return nfs_page_set_headlock(req->wb_head); +} + +/* + * nfs_page_group_unlock - unlock the head of the page group + * @req: request in group that is to be unlocked + */ +void +nfs_page_group_unlock(struct nfs_page *req) +{ + if (req != req->wb_head) + nfs_page_clear_headlock(req->wb_head); + nfs_page_clear_headlock(req); }

/* diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 63d20308a9bb..d419d89b91f7 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -416,22 +416,28 @@ nfs_destroy_unlinked_subrequests(struct nfs_page *destroy_list, destroy_list = (subreq->wb_this_page == old_head) ? NULL : subreq->wb_this_page;

+ /* Note: lock subreq in order to change subreq->wb_head */ + nfs_page_set_headlock(subreq); WARN_ON_ONCE(old_head != subreq->wb_head);

/* make sure old group is not used */ subreq->wb_this_page = subreq; + subreq->wb_head = subreq;

clear_bit(PG_REMOVE, &subreq->wb_flags);

/* Note: races with nfs_page_group_destroy() */ if (!kref_read(&subreq->wb_kref)) { /* Check if we raced with nfs_page_group_destroy() */ - if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags)) + if (test_and_clear_bit(PG_TEARDOWN, &subreq->wb_flags)) { + nfs_page_clear_headlock(subreq); nfs_free_request(subreq); + } else + nfs_page_clear_headlock(subreq); continue; } + nfs_page_clear_headlock(subreq);

- subreq->wb_head = subreq; nfs_release_request(old_head);

if (test_and_clear_bit(PG_INODE_REF, &subreq->wb_flags)) { diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index ad69430fd0eb..5162fc1533c2 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -142,6 +142,8 @@ extern void nfs_unlock_and_release_request(struct nfs_page *); extern int nfs_page_group_lock(struct nfs_page *); extern void nfs_page_group_unlock(struct nfs_page *); extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int); +extern int nfs_page_set_headlock(struct nfs_page *req); +extern void nfs_page_clear_headlock(struct nfs_page *req); extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *);

/*

From: Xianting Tian xianting_tian@126.com

[ Upstream commit faffdfa04fa11ccf048cebdde73db41ede0679e0 ]

Mount failure issue happens under the scenario: Application forked dozens of threads to mount the same number of cramfs images separately in docker, but several mounts failed with high probability. Mount failed due to the checking result of the page(read from the superblock of loop dev) is not uptodate after wait_on_page_locked(page) returned in function cramfs_read:

wait_on_page_locked(page); if (!PageUptodate(page)) { ... }

The reason of the checking result of the page not uptodate: systemd-udevd read the loopX dev before mount, because the status of loopX is Lo_unbound at this time, so loop_make_request directly trigger the calling of io_end handler end_buffer_async_read, which called SetPageError(page). So It caused the page can't be set to uptodate in function end_buffer_async_read:

if(page_uptodate && !PageError(page)) { SetPageUptodate(page); }

Then mount operation is performed, it used the same page which is just accessed by systemd-udevd above, Because this page is not uptodate, it will launch a actual read via submit_bh, then wait on this page by calling wait_on_page_locked(page). When the I/O of the page done, io_end handler end_buffer_async_read is called, because no one cleared the page error(during the whole read path of mount), which is caused by systemd-udevd reading, so this page is still in "PageError" status, which can't be set to uptodate in function end_buffer_async_read, then caused mount failure.

But sometimes mount succeed even through systemd-udeved read loopX dev just before, The reason is systemd-udevd launched other loopX read just between step 3.1 and 3.2, the steps as below:

1, loopX dev default status is Lo_unbound; 2, systemd-udved read loopX dev (page is set to PageError); 3, mount operation 1) set loopX status to Lo_bound; ==>systemd-udevd read loopX dev<== 2) read loopX dev(page has no error) 3) mount succeed

As the loopX dev status is set to Lo_bound after step 3.1, so the other loopX dev read by systemd-udevd will go through the whole I/O stack, part of the call trace as below:

SYS_read vfs_read do_sync_read blkdev_aio_read generic_file_aio_read do_generic_file_read: ClearPageError(page); mapping->a_ops->readpage(filp, page);

here, mapping->a_ops->readpage() is blkdev_readpage. In latest kernel, some function name changed, the call trace as below:

blkdev_read_iter generic_file_read_iter generic_file_buffered_read: /* * A previous I/O error may have been due to temporary * failures, eg. mutipath errors. * Pg_error will be set again if readpage fails. */ ClearPageError(page); /* Start the actual read. The read will unlock the page*/ error=mapping->a_ops->readpage(flip, page);

We can see ClearPageError(page) is called before the actual read, then the read in step 3.2 succeed.

This patch is to add the calling of ClearPageError just before the actual read of read path of cramfs mount. Without the patch, the call trace as below when performing cramfs mount:

do_mount cramfs_read cramfs_blkdev_read read_cache_page do_read_cache_page: filler(data, page); or mapping->a_ops->readpage(data, page);

With the patch, the call trace as below when performing mount:

do_mount cramfs_read cramfs_blkdev_read read_cache_page: do_read_cache_page: ClearPageError(page); <== new add filler(data, page); or mapping->a_ops->readpage(data, page);

With the patch, mount operation trigger the calling of ClearPageError(page) before the actual read, the page has no error if no additional page error happen when I/O done.

Signed-off-by: Xianting Tian xianting_tian@126.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Reviewed-by: Matthew Wilcox (Oracle) willy@infradead.org Cc: Jan Kara jack@suse.cz Cc: yubin@h3c.com Link: http://lkml.kernel.org/r/1583318844-22971-1-git-send-email-xianting_tian@126... Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- mm/filemap.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/mm/filemap.c b/mm/filemap.c index 55bb93ca0076..13f3276effd4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2979,6 +2979,14 @@ static struct page *do_read_cache_page(struct address_space *mapping, unlock_page(page); goto out; } + + /* + * A previous I/O error may have been due to temporary + * failures. + * Clear page error before actual read, PG_error will be + * set again if read page fails. + */ + ClearPageError(page); goto filler;

out:

From: Israel Rukshin israelr@mellanox.com

[ Upstream commit 21f9024355e58772ec5d7fc3534aa5e29d72a8b6 ]

In case rdma accept fails at nvmet_rdma_queue_connect(), release work is scheduled. Later on, a new RDMA CM event may arrive since we didn't destroy the cm-id and call nvmet_rdma_queue_connect_fail(), which schedule another release work. This will cause calling nvmet_rdma_free_queue twice. To fix this we implicitly destroy the cm_id with non-zero ret code, which guarantees that new rdma_cm events will not arrive afterwards. Also add a qp pointer to nvmet_rdma_queue structure, so we can use it when the cm_id pointer is NULL or was destroyed.

Signed-off-by: Israel Rukshin israelr@mellanox.com Suggested-by: Sagi Grimberg sagi@grimberg.me Reviewed-by: Max Gurtovoy maxg@mellanox.com Reviewed-by: Sagi Grimberg sagi@grimberg.me Signed-off-by: Christoph Hellwig hch@lst.de Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/nvme/target/rdma.c | 30 ++++++++++++++++++------------ 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c index 08f997a390d5..cfd26437aeae 100644 --- a/drivers/nvme/target/rdma.c +++ b/drivers/nvme/target/rdma.c @@ -83,6 +83,7 @@ enum nvmet_rdma_queue_state {

struct nvmet_rdma_queue { struct rdma_cm_id *cm_id; + struct ib_qp *qp; struct nvmet_port *port; struct ib_cq *cq; atomic_t sq_wr_avail; @@ -471,7 +472,7 @@ static int nvmet_rdma_post_recv(struct nvmet_rdma_device *ndev, if (ndev->srq) ret = ib_post_srq_recv(ndev->srq, &cmd->wr, NULL); else - ret = ib_post_recv(cmd->queue->cm_id->qp, &cmd->wr, NULL); + ret = ib_post_recv(cmd->queue->qp, &cmd->wr, NULL);

if (unlikely(ret)) pr_err("post_recv cmd failed\n"); @@ -510,7 +511,7 @@ static void nvmet_rdma_release_rsp(struct nvmet_rdma_rsp *rsp) atomic_add(1 + rsp->n_rdma, &queue->sq_wr_avail);

if (rsp->n_rdma) { - rdma_rw_ctx_destroy(&rsp->rw, queue->cm_id->qp, + rdma_rw_ctx_destroy(&rsp->rw, queue->qp, queue->cm_id->port_num, rsp->req.sg, rsp->req.sg_cnt, nvmet_data_dir(&rsp->req)); } @@ -594,7 +595,7 @@ static void nvmet_rdma_read_data_done(struct ib_cq *cq, struct ib_wc *wc)

WARN_ON(rsp->n_rdma <= 0); atomic_add(rsp->n_rdma, &queue->sq_wr_avail); - rdma_rw_ctx_destroy(&rsp->rw, queue->cm_id->qp, + rdma_rw_ctx_destroy(&rsp->rw, queue->qp, queue->cm_id->port_num, rsp->req.sg, rsp->req.sg_cnt, nvmet_data_dir(&rsp->req)); rsp->n_rdma = 0; @@ -737,7 +738,7 @@ static bool nvmet_rdma_execute_command(struct nvmet_rdma_rsp *rsp) }

if (nvmet_rdma_need_data_in(rsp)) { - if (rdma_rw_ctx_post(&rsp->rw, queue->cm_id->qp, + if (rdma_rw_ctx_post(&rsp->rw, queue->qp, queue->cm_id->port_num, &rsp->read_cqe, NULL)) nvmet_req_complete(&rsp->req, NVME_SC_DATA_XFER_ERROR); } else { @@ -1020,6 +1021,7 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue) pr_err("failed to create_qp ret= %d\n", ret); goto err_destroy_cq; } + queue->qp = queue->cm_id->qp;

atomic_set(&queue->sq_wr_avail, qp_attr.cap.max_send_wr);

@@ -1048,11 +1050,10 @@ static int nvmet_rdma_create_queue_ib(struct nvmet_rdma_queue *queue)

static void nvmet_rdma_destroy_queue_ib(struct nvmet_rdma_queue *queue) { - struct ib_qp *qp = queue->cm_id->qp; - - ib_drain_qp(qp); - rdma_destroy_id(queue->cm_id); - ib_destroy_qp(qp); + ib_drain_qp(queue->qp); + if (queue->cm_id) + rdma_destroy_id(queue->cm_id); + ib_destroy_qp(queue->qp); ib_free_cq(queue->cq); }

@@ -1286,9 +1287,12 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id,

ret = nvmet_rdma_cm_accept(cm_id, queue, &event->param.conn); if (ret) { - schedule_work(&queue->release_work); - /* Destroying rdma_cm id is not needed here */ - return 0; + /* + * Don't destroy the cm_id in free path, as we implicitly + * destroy the cm_id here with non-zero ret code. + */ + queue->cm_id = NULL; + goto free_queue; }

mutex_lock(&nvmet_rdma_queue_mutex); @@ -1297,6 +1301,8 @@ static int nvmet_rdma_queue_connect(struct rdma_cm_id *cm_id,

return 0;

+free_queue: + nvmet_rdma_free_queue(queue); put_device: kref_put(&ndev->ref, nvmet_rdma_free_dev);

From: Nilesh Javali njavali@marvell.com

[ Upstream commit b9b97e6903032ec56e6dcbe137a9819b74a17fea ]

The destroy connection ramrod timed out during session logout. Fix the wait delay for graceful vs abortive termination as per the FW requirements.

Link: https://lore.kernel.org/r/20200408064332.19377-7-mrangankar@marvell.com Reviewed-by: Lee Duncan lduncan@suse.com Signed-off-by: Nilesh Javali njavali@marvell.com Signed-off-by: Manish Rangankar mrangankar@marvell.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/scsi/qedi/qedi_iscsi.c | 3 +++ 1 file changed, 3 insertions(+)

diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index 751941a3ed30..aa451c8b49e5 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -1065,6 +1065,9 @@ static void qedi_ep_disconnect(struct iscsi_endpoint *ep) break; }

+ if (!abrt_conn) + wait_delay += qedi->pf_params.iscsi_pf_params.two_msl_timer; + qedi_ep->state = EP_STATE_DISCONN_START; ret = qedi_ops->destroy_conn(qedi->cdev, qedi_ep->handle, abrt_conn); if (ret) {

From: Steve Rutherford srutherford@google.com

[ Upstream commit 7289fdb5dcdbc5155b5531529c44105868a762f2 ]

Fixes a NULL pointer dereference, caused by the PIT firing an interrupt before the interrupt table has been initialized.

SET_PIT2 can race with the creation of the IRQchip. In particular, if SET_PIT2 is called with a low PIT timer period (after the creation of the IOAPIC, but before the instantiation of the irq routes), the PIT can fire an interrupt at an uninitialized table.

Signed-off-by: Steve Rutherford srutherford@google.com Signed-off-by: Jon Cargille jcargill@google.com Reviewed-by: Jim Mattson jmattson@google.com Message-Id: 20200416191152.259434-1-jcargill@google.com Signed-off-by: Paolo Bonzini pbonzini@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- arch/x86/kvm/x86.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cd25b6209047..0cbe674d23b3 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -4685,10 +4685,13 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&u.ps, argp, sizeof u.ps)) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit_out; r = kvm_vm_ioctl_set_pit(kvm, &u.ps); +set_pit_out: + mutex_unlock(&kvm->lock); break; } case KVM_GET_PIT2: { @@ -4708,10 +4711,13 @@ long kvm_arch_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&u.ps2, argp, sizeof(u.ps2))) goto out; + mutex_lock(&kvm->lock); r = -ENXIO; if (!kvm->arch.vpit) - goto out; + goto set_pit2_out; r = kvm_vm_ioctl_set_pit2(kvm, &u.ps2); +set_pit2_out: + mutex_unlock(&kvm->lock); break; } case KVM_REINJECT_CONTROL: {

From: Madhuparna Bhowmik madhuparnabhowmik10@gmail.com

[ Upstream commit 44b8fb6eaa7c3fb770bf1e37619cdb3902cca1fc ]

After registering character device the file operation callbacks can be called. The open callback registers interrupt handler. Therefore interrupt handler can execute in parallel with rest of the init function. To avoid such data race initialize telclk_interrupt variable and struct alarm_events before registering character device.

Found by Linux Driver Verification project (linuxtesting.org).

Signed-off-by: Madhuparna Bhowmik madhuparnabhowmik10@gmail.com Link: https://lore.kernel.org/r/20200417153451.1551-1-madhuparnabhowmik10@gmail.co... Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/char/tlclk.c | 17 ++++++++++------- 1 file changed, 10 insertions(+), 7 deletions(-)

diff --git a/drivers/char/tlclk.c b/drivers/char/tlclk.c index 8eeb4190207d..dce22b7fc544 100644 --- a/drivers/char/tlclk.c +++ b/drivers/char/tlclk.c @@ -776,17 +776,21 @@ static int __init tlclk_init(void) { int ret;

+ telclk_interrupt = (inb(TLCLK_REG7) & 0x0f); + + alarm_events = kzalloc( sizeof(struct tlclk_alarms), GFP_KERNEL); + if (!alarm_events) { + ret = -ENOMEM; + goto out1; + } + ret = register_chrdev(tlclk_major, "telco_clock", &tlclk_fops); if (ret < 0) { printk(KERN_ERR "tlclk: can't get major %d.\n", tlclk_major); + kfree(alarm_events); return ret; } tlclk_major = ret; - alarm_events = kzalloc( sizeof(struct tlclk_alarms), GFP_KERNEL); - if (!alarm_events) { - ret = -ENOMEM; - goto out1; - }

/* Read telecom clock IRQ number (Set by BIOS) */ if (!request_region(TLCLK_BASE, 8, "telco_clock")) { @@ -795,7 +799,6 @@ static int __init tlclk_init(void) ret = -EBUSY; goto out2; } - telclk_interrupt = (inb(TLCLK_REG7) & 0x0f);

if (0x0F == telclk_interrupt ) { /* not MCPBL0010 ? */ printk(KERN_ERR "telclk_interrupt = 0x%x non-mcpbl0010 hw.\n", @@ -836,8 +839,8 @@ static int __init tlclk_init(void) release_region(TLCLK_BASE, 8); out2: kfree(alarm_events); -out1: unregister_chrdev(tlclk_major, "telco_clock"); +out1: return ret; }

From: Tonghao Zhang xiangxia.m.yue@gmail.com

[ Upstream commit e57358873bb5d6caa882b9684f59140912b37dde ]

When setting the meter rate to 4+Gbps, there is an overflow, the meters don't work as expected.

Cc: Pravin B Shelar pshelar@ovn.org Cc: Andy Zhou azhou@ovn.org Signed-off-by: Tonghao Zhang xiangxia.m.yue@gmail.com Acked-by: Pravin B Shelar pshelar@ovn.org Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- net/openvswitch/meter.c | 2 +- net/openvswitch/meter.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index c038e021a591..6f5131d1074b 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -255,7 +255,7 @@ static struct dp_meter *dp_meter_create(struct nlattr **a) * * Start with a full bucket. */ - band->bucket = (band->burst_size + band->rate) * 1000; + band->bucket = (band->burst_size + band->rate) * 1000ULL; band_max_delta_t = band->bucket / band->rate; if (band_max_delta_t > meter->max_delta_t) meter->max_delta_t = band_max_delta_t; diff --git a/net/openvswitch/meter.h b/net/openvswitch/meter.h index 964ace2650f8..970557ed5b5b 100644 --- a/net/openvswitch/meter.h +++ b/net/openvswitch/meter.h @@ -26,7 +26,7 @@ struct dp_meter_band { u32 type; u32 rate; u32 burst_size; - u32 bucket; /* 1/1000 packets, or in bits */ + u64 bucket; /* 1/1000 packets, or in bits */ struct ovs_flow_stats stats; };

From: Ivan Safonov insafonov@gmail.com

[ Upstream commit 628cbd971a927abe6388d44320e351c337b331e4 ]

skb clones use same data buffer, so tail of one skb is corrupted by beginning of next skb.

Signed-off-by: Ivan Safonov insafonov@gmail.com Link: https://lore.kernel.org/r/20200423191404.12028-1-insafonov@gmail.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/staging/rtl8188eu/core/rtw_recv.c | 19 ++++++------------- 1 file changed, 6 insertions(+), 13 deletions(-)

diff --git a/drivers/staging/rtl8188eu/core/rtw_recv.c b/drivers/staging/rtl8188eu/core/rtw_recv.c index 17b4b9257b49..0ddf41b5a734 100644 --- a/drivers/staging/rtl8188eu/core/rtw_recv.c +++ b/drivers/staging/rtl8188eu/core/rtw_recv.c @@ -1535,21 +1535,14 @@ static int amsdu_to_msdu(struct adapter *padapter, struct recv_frame *prframe)

/* Allocate new skb for releasing to upper layer */ sub_skb = dev_alloc_skb(nSubframe_Length + 12); - if (sub_skb) { - skb_reserve(sub_skb, 12); - skb_put_data(sub_skb, pdata, nSubframe_Length); - } else { - sub_skb = skb_clone(prframe->pkt, GFP_ATOMIC); - if (sub_skb) { - sub_skb->data = pdata; - sub_skb->len = nSubframe_Length; - skb_set_tail_pointer(sub_skb, nSubframe_Length); - } else { - DBG_88E("skb_clone() Fail!!! , nr_subframes=%d\n", nr_subframes); - break; - } + if (!sub_skb) { + DBG_88E("dev_alloc_skb() Fail!!! , nr_subframes=%d\n", nr_subframes); + break; }

+ skb_reserve(sub_skb, 12); + skb_put_data(sub_skb, pdata, nSubframe_Length); + subframes[nr_subframes++] = sub_skb;

if (nr_subframes >= MAX_SUBFRAME_COUNT) {

From: Will Deacon will@kernel.org

[ Upstream commit 98448cdfe7060dd5491bfbd3f7214ffe1395d58e ]

We don't need to be quite as strict about mismatched AArch32 support, which is good because the friendly hardware folks have been busy mismatching this to their hearts' content.

* We don't care about EL2 or EL3 (there are silly comments concerning the latter, so remove those)

* EL1 support is gated by the ARM64_HAS_32BIT_EL1 capability and handled gracefully when a mismatch occurs

* EL0 support is gated by the ARM64_HAS_32BIT_EL0 capability and handled gracefully when a mismatch occurs

Relax the AArch32 checks to FTR_NONSTRICT.

Tested-by: Sai Prakash Ranjan saiprakash.ranjan@codeaurora.org Reviewed-by: Suzuki K Poulose suzuki.poulose@arm.com Link: https://lore.kernel.org/r/20200421142922.18950-8-will@kernel.org Signed-off-by: Will Deacon will@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- arch/arm64/kernel/cpufeature.c | 10 +++------- 1 file changed, 3 insertions(+), 7 deletions(-)

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 191cb8beddda..98238dfa3347 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -183,11 +183,10 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_GIC_SHIFT, 4, 0), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_ASIMD_SHIFT, 4, ID_AA64PFR0_ASIMD_NI), S_ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_FP_SHIFT, 4, ID_AA64PFR0_FP_NI), - /* Linux doesn't care about the EL3 */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL3_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), - ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL2_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL1_SHIFT, 4, ID_AA64PFR0_EL1_64BIT_ONLY), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64PFR0_EL0_SHIFT, 4, ID_AA64PFR0_EL0_64BIT_ONLY), ARM64_FTR_END, };

@@ -752,9 +751,6 @@ void update_cpu_features(int cpu, taint |= check_update_ftr_reg(SYS_ID_AA64MMFR2_EL1, cpu, info->reg_id_aa64mmfr2, boot->reg_id_aa64mmfr2);

- /* - * EL3 is not our concern. - */ taint |= check_update_ftr_reg(SYS_ID_AA64PFR0_EL1, cpu, info->reg_id_aa64pfr0, boot->reg_id_aa64pfr0); taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu,

From: Cong Wang xiyou.wangcong@gmail.com

[ Upstream commit 8d9f73c0ad2f20e9fed5380de0a3097825859d03 ]

In lec_arp_clear_vccs() only entry->vcc is freed, but vcc could be installed on entry->recv_vcc too in lec_vcc_added().

This fixes the following memory leak:

unreferenced object 0xffff8880d9266b90 (size 16): comm "atm2", pid 425, jiffies 4294907980 (age 23.488s) hex dump (first 16 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 6b 6b 6b a5 ............kkk. backtrace: [<(____ptrval____)>] kmem_cache_alloc_trace+0x10e/0x151 [<(____ptrval____)>] lane_ioctl+0x4b3/0x569 [<(____ptrval____)>] do_vcc_ioctl+0x1ea/0x236 [<(____ptrval____)>] svc_ioctl+0x17d/0x198 [<(____ptrval____)>] sock_do_ioctl+0x47/0x12f [<(____ptrval____)>] sock_ioctl+0x2f9/0x322 [<(____ptrval____)>] vfs_ioctl+0x1e/0x2b [<(____ptrval____)>] ksys_ioctl+0x61/0x80 [<(____ptrval____)>] __x64_sys_ioctl+0x16/0x19 [<(____ptrval____)>] do_syscall_64+0x57/0x65 [<(____ptrval____)>] entry_SYSCALL_64_after_hwframe+0x49/0xb3

Cc: Gengming Liu l.dmxcsnsbh@gmail.com Signed-off-by: Cong Wang xiyou.wangcong@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- net/atm/lec.c | 6 ++++++ 1 file changed, 6 insertions(+)

diff --git a/net/atm/lec.c b/net/atm/lec.c index ad4f829193f0..5a6186b80987 100644 --- a/net/atm/lec.c +++ b/net/atm/lec.c @@ -1270,6 +1270,12 @@ static void lec_arp_clear_vccs(struct lec_arp_table *entry) entry->vcc = NULL; } if (entry->recv_vcc) { + struct atm_vcc *vcc = entry->recv_vcc; + struct lec_vcc_priv *vpriv = LEC_VCC_PRIV(vcc); + + kfree(vpriv); + vcc->user_back = NULL; + entry->recv_vcc->push = entry->old_recv_push; vcc_release_async(entry->recv_vcc, -EPIPE); entry->recv_vcc = NULL;

From: Jonathan Bakker xc-racer2@live.ca

[ Upstream commit 0383024f811aa469df258039807810fc3793a105 ]

According to the datasheet available at (1), the bottom four bits are always zero and the actual voltage is 1.25x this value in mV. Since the kernel API specifies that voltages should be in uV, it should report 1250x the shifted value.

1) https://datasheets.maximintegrated.com/en/ds/MAX17040-MAX17041.pdf

Signed-off-by: Jonathan Bakker xc-racer2@live.ca Signed-off-by: Sebastian Reichel sebastian.reichel@collabora.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- drivers/power/supply/max17040_battery.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/power/supply/max17040_battery.c b/drivers/power/supply/max17040_battery.c index 33c40f79d23d..2c35c13ad546 100644 --- a/drivers/power/supply/max17040_battery.c +++ b/drivers/power/supply/max17040_battery.c @@ -109,7 +109,7 @@ static void max17040_get_vcell(struct i2c_client *client)

vcell = max17040_read_reg(client, MAX17040_VCELL);

- chip->vcell = vcell; + chip->vcell = (vcell >> 4) * 1250; }

static void max17040_get_soc(struct i2c_client *client)

From: Sonny Sasaka sonnysasaka@chromium.org

[ Upstream commit adf1d6926444029396861413aba8a0f2a805742a ]

After sending Inquiry Cancel command to the controller, it is possible that Inquiry Complete event comes before Inquiry Cancel command complete event. In this case the Inquiry Cancel command will have status of Command Disallowed since there is no Inquiry session to be cancelled. This case should not be treated as error, otherwise we can reach an inconsistent state.

Example of a btmon trace when this happened:

< HCI Command: Inquiry Cancel (0x01|0x0002) plen 0

HCI Event: Inquiry Complete (0x01) plen 1

Status: Success (0x00)

HCI Event: Command Complete (0x0e) plen 4

Inquiry Cancel (0x01|0x0002) ncmd 1 Status: Command Disallowed (0x0c)

Signed-off-by: Sonny Sasaka sonnysasaka@chromium.org Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- net/bluetooth/hci_event.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-)

diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index ec6b3a87b3e7..310622086f74 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -41,12 +41,27 @@

/* Handle HCI Event packets */

-static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb) +static void hci_cc_inquiry_cancel(struct hci_dev *hdev, struct sk_buff *skb, + u8 *new_status) { __u8 status = *((__u8 *) skb->data);

BT_DBG("%s status 0x%2.2x", hdev->name, status);

+ /* It is possible that we receive Inquiry Complete event right + * before we receive Inquiry Cancel Command Complete event, in + * which case the latter event should have status of Command + * Disallowed (0x0c). This should not be treated as error, since + * we actually achieve what Inquiry Cancel wants to achieve, + * which is to end the last Inquiry session. + */ + if (status == 0x0c && !test_bit(HCI_INQUIRY, &hdev->flags)) { + bt_dev_warn(hdev, "Ignoring error of Inquiry Cancel command"); + status = 0x00; + } + + *new_status = status; + if (status) return;

@@ -3039,7 +3054,7 @@ static void hci_cmd_complete_evt(struct hci_dev *hdev, struct sk_buff *skb,

switch (*opcode) { case HCI_OP_INQUIRY_CANCEL: - hci_cc_inquiry_cancel(hdev, skb); + hci_cc_inquiry_cancel(hdev, skb, status); break;

case HCI_OP_PERIODIC_INQ:

From: Tuong Lien tuong.t.lien@dektech.com.au

[ Upstream commit 0771d7df819284d46cf5cfb57698621b503ec17f ]

Upon receipt of a service subscription request from user via a topology connection, one 'sub' object will be allocated in kernel, so it will be able to send an event of the service if any to the user correspondingly then. Also, in case of any failure, the connection will be shutdown and all the pertaining 'sub' objects will be freed.

However, there is a race condition as follows resulting in memory leak:

receive-work connection send-work | | | sub-1 |<------//-------| | sub-2 |<------//-------| | | |<---------------| evt for sub-x sub-3 |<------//-------| | : : : : : : | /--------| | | | * peer closed | | | | | | | |<-------X-------| evt for sub-y | | |<===============| sub-n |<------/ X shutdown | -> orphan | |

That is, the 'receive-work' may get the last subscription request while the 'send-work' is shutting down the connection due to peer close.

We had a 'lock' on the connection, so the two actions cannot be carried out simultaneously. If the last subscription is allocated e.g. 'sub-n', before the 'send-work' closes the connection, there will be no issue at all, the 'sub' objects will be freed. In contrast the last subscription will become orphan since the connection was closed, and we released all references.

This commit fixes the issue by simply adding one test if the connection remains in 'connected' state right after we obtain the connection lock, then a subscription object can be created as usual, otherwise we ignore it.

Acked-by: Ying Xue ying.xue@windriver.com Acked-by: Jon Maloy jmaloy@redhat.com Reported-by: Thang Ngo thang.h.ngo@dektech.com.au Signed-off-by: Tuong Lien tuong.t.lien@dektech.com.au Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- net/tipc/topsrv.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 41f4464ac6cc..ec9a7137d267 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -407,7 +407,9 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) return -EWOULDBLOCK; if (ret == sizeof(s)) { read_lock_bh(&sk->sk_callback_lock); - ret = tipc_conn_rcv_sub(srv, con, &s); + /* RACE: the connection can be closed in the meantime */ + if (likely(connected(con))) + ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); if (!ret) return 0;

From: Takashi Iwai tiwai@suse.de

[ Upstream commit c637fa151259c0f74665fde7cba5b7eac1417ae5 ]

The unsol event handling code has a loop retrieving the read/write indices and the arrays without locking while the append to the array may happen concurrently. This may lead to some inconsistency. Although there hasn't been any proof of this bad results, it's still safer to protect the racy accesses.

This patch adds the spinlock protection around the unsol handling loop for addressing it. Here we take bus->reg_lock as the writer side snd_hdac_bus_queue_event() is also protected by that lock.

Link: https://lore.kernel.org/r/20200516062556.30951-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- sound/hda/hdac_bus.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/sound/hda/hdac_bus.c b/sound/hda/hdac_bus.c index 714a51721a31..ab9236e4c157 100644 --- a/sound/hda/hdac_bus.c +++ b/sound/hda/hdac_bus.c @@ -155,6 +155,7 @@ static void process_unsol_events(struct work_struct *work) struct hdac_driver *drv; unsigned int rp, caddr, res;

+ spin_lock_irq(&bus->reg_lock); while (bus->unsol_rp != bus->unsol_wp) { rp = (bus->unsol_rp + 1) % HDA_UNSOL_QUEUE_SIZE; bus->unsol_rp = rp; @@ -166,10 +167,13 @@ static void process_unsol_events(struct work_struct *work) codec = bus->caddr_tbl[caddr & 0x0f]; if (!codec || !codec->dev.driver) continue; + spin_unlock_irq(&bus->reg_lock); drv = drv_to_hdac_driver(codec->dev.driver); if (drv->unsol_event) drv->unsol_event(codec, res); + spin_lock_irq(&bus->reg_lock); } + spin_unlock_irq(&bus->reg_lock); }

/**

From: Miklos Szeredi mszeredi@redhat.com

[ Upstream commit 32f98877c57bee6bc27f443a96f49678a2cd6a50 ]

page_count() is unstable. Unless there has been an RCU grace period between when the page was removed from the page cache and now, a speculative reference may exist from the page cache.

Reported-by: Matthew Wilcox willy@infradead.org Signed-off-by: Miklos Szeredi mszeredi@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org Signed-off-by: Yang Yingliang yangyingliang@huawei.com --- fs/fuse/dev.c | 1 - 1 file changed, 1 deletion(-)

diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 01e6ea11822b..c51c9a6881e4 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -831,7 +831,6 @@ static int fuse_check_page(struct page *page) { if (page_mapcount(page) || page->mapping != NULL || - page_count(page) != 1 || (page->flags & PAGE_FLAGS_CHECK_AT_PREP & ~(1 << PG_locked | 1 << PG_referenced |