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 --- 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 ed518b1f82e4a..d04ed438a45de 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 --- 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 0baaad90b8d18..aa333110eaba6 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 3372dfa0deccf..3f3fbee631c34 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 --- mm/memory.c | 104 ++++++++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 89 insertions(+), 15 deletions(-)

diff --git a/mm/memory.c b/mm/memory.c index bbf0cc4066c84..fcad8a0d943d3 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -116,6 +116,18 @@ 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; @@ -2335,32 +2347,82 @@ 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) @@ -2514,7 +2576,19 @@ 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 --- 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 96810d91da2bd..4a25ce6a1823d 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 --- 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 c6a58520d377a..255cc45905b81 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

--- arch/x86/lib/usercopy_64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/arch/x86/lib/usercopy_64.c +++ b/arch/x86/lib/usercopy_64.c @@ -139,7 +139,7 @@ long __copy_user_flushcache(void *dst, c */ 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

--- sound/usb/quirks.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

--- a/sound/usb/quirks.c +++ b/sound/usb/quirks.c @@ -1338,12 +1338,13 @@ void snd_usb_ctl_msg_quirk(struct usb_de && (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

--- sound/pci/hda/patch_realtek.c | 7 +++++++ 1 file changed, 7 insertions(+)

--- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -5616,6 +5616,7 @@ static void alc_fixup_thinkpad_acpi(stru #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_fix [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 --- 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 1ee48cb21df95..022e973dc7c31 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 --- 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 73ffc16ec0225..b521fc7650cb9 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 --- 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 1e0cc96306dd7..2c1f3ddb0cc79 100644 --- a/drivers/crypto/chelsio/chtls/chtls_io.c +++ b/drivers/crypto/chelsio/chtls/chtls_io.c @@ -1449,7 +1449,7 @@ 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) { @@ -1482,7 +1482,7 @@ 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); @@ -1627,7 +1627,7 @@ 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); @@ -1759,7 +1759,7 @@ 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) { @@ -1790,7 +1790,7 @@ 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 77f36257cac97..bc752237dff3f 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -900,11 +900,11 @@ 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 616ff2970f4fc..4ce3397e6fcf7 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 6ead3c39f3566..bcba579e292ff 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -785,7 +785,7 @@ 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 --- 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 ce459ea4ec3ad..da9e6923fa659 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 --- 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 182973df1aed4..77c965c6a65f1 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 --- 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 763fc7e6c0058..20f27100708bd 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: Guoju Fang fangguoju@gmail.com

[ Upstream commit 34cf78bf34d48dddddfeeadb44f9841d7864997a ]

This patch fix a lost wake-up problem caused by the race between mca_cannibalize_lock and bch_cannibalize_unlock.

Consider two processes, A and B. Process A is executing mca_cannibalize_lock, while process B takes c->btree_cache_alloc_lock and is executing bch_cannibalize_unlock. The problem happens that after process A executes cmpxchg and will execute prepare_to_wait. In this timeslice process B executes wake_up, but after that process A executes prepare_to_wait and set the state to TASK_INTERRUPTIBLE. Then process A goes to sleep but no one will wake up it. This problem may cause bcache device to dead.

Signed-off-by: Guoju Fang fangguoju@gmail.com Signed-off-by: Coly Li colyli@suse.de Signed-off-by: Jens Axboe axboe@kernel.dk Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/md/bcache/bcache.h | 1 + drivers/md/bcache/btree.c | 12 ++++++++---- drivers/md/bcache/super.c | 1 + 3 files changed, 10 insertions(+), 4 deletions(-)

diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 1cc6ae3e058c6..6a380ed4919a0 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -585,6 +585,7 @@ struct cache_set { */ wait_queue_head_t btree_cache_wait; struct task_struct *btree_cache_alloc_lock; + spinlock_t btree_cannibalize_lock;

/* * When we free a btree node, we increment the gen of the bucket the diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index d320574b9a4c8..e388e7bb7b5db 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -876,15 +876,17 @@ out:

static int mca_cannibalize_lock(struct cache_set *c, struct btree_op *op) { - struct task_struct *old; - - old = cmpxchg(&c->btree_cache_alloc_lock, NULL, current); - if (old && old != current) { + spin_lock(&c->btree_cannibalize_lock); + if (likely(c->btree_cache_alloc_lock == NULL)) { + c->btree_cache_alloc_lock = current; + } else if (c->btree_cache_alloc_lock != current) { if (op) prepare_to_wait(&c->btree_cache_wait, &op->wait, TASK_UNINTERRUPTIBLE); + spin_unlock(&c->btree_cannibalize_lock); return -EINTR; } + spin_unlock(&c->btree_cannibalize_lock);

return 0; } @@ -919,10 +921,12 @@ static struct btree *mca_cannibalize(struct cache_set *c, struct btree_op *op, */ static void bch_cannibalize_unlock(struct cache_set *c) { + spin_lock(&c->btree_cannibalize_lock); if (c->btree_cache_alloc_lock == current) { c->btree_cache_alloc_lock = NULL; wake_up(&c->btree_cache_wait); } + spin_unlock(&c->btree_cannibalize_lock); }

static struct btree *mca_alloc(struct cache_set *c, struct btree_op *op, diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index 825bfde10c694..7787ec42f81e1 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1737,6 +1737,7 @@ struct cache_set *bch_cache_set_alloc(struct cache_sb *sb) sema_init(&c->sb_write_mutex, 1); mutex_init(&c->bucket_lock); init_waitqueue_head(&c->btree_cache_wait); + spin_lock_init(&c->btree_cannibalize_lock); init_waitqueue_head(&c->bucket_wait); init_waitqueue_head(&c->gc_wait); sema_init(&c->uuid_write_mutex, 1);

From: Pan Bian bianpan2016@163.com

[ Upstream commit 960657b732e1ce21b07be5ab48a7ad3913d72ba4 ]

Move the release operation after error log to avoid possible use after free.

Link: https://lore.kernel.org/r/1573021434-18768-1-git-send-email-bianpan2016@163.... Signed-off-by: Pan Bian bianpan2016@163.com Acked-by: Michal Kalderon michal.kalderon@marvell.com Reviewed-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/qedr/qedr_iw_cm.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/infiniband/hw/qedr/qedr_iw_cm.c b/drivers/infiniband/hw/qedr/qedr_iw_cm.c index 2566715773675..e908dfbaa1378 100644 --- a/drivers/infiniband/hw/qedr/qedr_iw_cm.c +++ b/drivers/infiniband/hw/qedr/qedr_iw_cm.c @@ -460,10 +460,10 @@ qedr_addr6_resolve(struct qedr_dev *dev,

if ((!dst) || dst->error) { if (dst) { - dst_release(dst); DP_ERR(dev, "ip6_route_output returned dst->error = %d\n", dst->error); + dst_release(dst); } return -EINVAL; }

From: Al Viro viro@zeniv.linux.org.uk

[ Upstream commit e84009336711d2bba885fc9cea66348ddfce3758 ]

We are overoptimistic about taking the fast path there; seeing the same value in ->d_parent after having grabbed a reference to that parent does *not* mean that it has remained our parent all along.

That wouldn't be a big deal (in the end it is our parent and we have grabbed the reference we are about to return), but... the situation with barriers is messed up.

We might have hit the following sequence:

d is a dentry of /tmp/a/b CPU1: CPU2: parent = d->d_parent (i.e. dentry of /tmp/a) rename /tmp/a/b to /tmp/b rmdir /tmp/a, making its dentry negative grab reference to parent, end up with cached parent->d_inode (NULL) mkdir /tmp/a, rename /tmp/b to /tmp/a/b recheck d->d_parent, which is back to original decide that everything's fine and return the reference we'd got.

The trouble is, caller (on CPU1) will observe dget_parent() returning an apparently negative dentry. It actually is positive, but CPU1 has stale ->d_inode cached.

Use d->d_seq to see if it has been moved instead of rechecking ->d_parent. NOTE: we are *NOT* going to retry on any kind of ->d_seq mismatch; we just go into the slow path in such case. We don't wait for ->d_seq to become even either - again, if we are racing with renames, we can bloody well go to slow path anyway.

Signed-off-by: Al Viro viro@zeniv.linux.org.uk Signed-off-by: Sasha Levin sashal@kernel.org --- fs/dcache.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/fs/dcache.c b/fs/dcache.c index 6e0022326afe3..20370a0997bf9 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -864,17 +864,19 @@ struct dentry *dget_parent(struct dentry *dentry) { int gotref; struct dentry *ret; + unsigned seq;

/* * Do optimistic parent lookup without any * locking. */ rcu_read_lock(); + seq = raw_seqcount_begin(&dentry->d_seq); ret = READ_ONCE(dentry->d_parent); gotref = lockref_get_not_zero(&ret->d_lockref); rcu_read_unlock(); if (likely(gotref)) { - if (likely(ret == READ_ONCE(dentry->d_parent))) + if (!read_seqcount_retry(&dentry->d_seq, seq)) return ret; dput(ret); }

From: Christophe JAILLET christophe.jaillet@wanadoo.fr

[ Upstream commit 9067f2f0b41d7e817fc8c5259bab1f17512b0147 ]

We should jump to fail3 in order to undo the 'xa_insert_irq()' call.

Link: https://lore.kernel.org/r/20190923190746.10964-1-christophe.jaillet@wanadoo.... Signed-off-by: Christophe JAILLET christophe.jaillet@wanadoo.fr Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/hw/cxgb4/cm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c index 16145b0a14583..3fd3dfa3478b7 100644 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@ -3293,7 +3293,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) if (raddr->sin_addr.s_addr == htonl(INADDR_ANY)) { err = pick_local_ipaddrs(dev, cm_id); if (err) - goto fail2; + goto fail3; }

/* find a route */ @@ -3315,7 +3315,7 @@ int c4iw_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param) if (ipv6_addr_type(&raddr6->sin6_addr) == IPV6_ADDR_ANY) { err = pick_local_ip6addrs(dev, cm_id); if (err) - goto fail2; + goto fail3; }

/* find a route */

From: Bradley Bolen bradleybolen@gmail.com

[ Upstream commit f3d7c2292d104519195fdb11192daec13229c219 ]

With large eMMC cards, it is possible to create general purpose partitions that are bigger than 4GB. The size member of the mmc_part struct is only an unsigned int which overflows for gp partitions larger than 4GB. Change this to a u64 to handle the overflow.

Signed-off-by: Bradley Bolen bradleybolen@gmail.com Signed-off-by: Ulf Hansson ulf.hansson@linaro.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/mmc/core/mmc.c | 9 ++++----- include/linux/mmc/card.h | 2 +- 2 files changed, 5 insertions(+), 6 deletions(-)

diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c index 5ca53e225382d..4b18034537f53 100644 --- a/drivers/mmc/core/mmc.c +++ b/drivers/mmc/core/mmc.c @@ -300,7 +300,7 @@ static void mmc_manage_enhanced_area(struct mmc_card *card, u8 *ext_csd) } }

-static void mmc_part_add(struct mmc_card *card, unsigned int size, +static void mmc_part_add(struct mmc_card *card, u64 size, unsigned int part_cfg, char *name, int idx, bool ro, int area_type) { @@ -316,7 +316,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd) { int idx; u8 hc_erase_grp_sz, hc_wp_grp_sz; - unsigned int part_size; + u64 part_size;

/* * General purpose partition feature support -- @@ -346,8 +346,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd) (ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3 + 1] << 8) + ext_csd[EXT_CSD_GP_SIZE_MULT + idx * 3]; - part_size *= (size_t)(hc_erase_grp_sz * - hc_wp_grp_sz); + part_size *= (hc_erase_grp_sz * hc_wp_grp_sz); mmc_part_add(card, part_size << 19, EXT_CSD_PART_CONFIG_ACC_GP0 + idx, "gp%d", idx, false, @@ -365,7 +364,7 @@ static void mmc_manage_gp_partitions(struct mmc_card *card, u8 *ext_csd) static int mmc_decode_ext_csd(struct mmc_card *card, u8 *ext_csd) { int err = 0, idx; - unsigned int part_size; + u64 part_size; struct device_node *np; bool broken_hpi = false;

diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h index 8ef330027b134..3f8e84a80b4ad 100644 --- a/include/linux/mmc/card.h +++ b/include/linux/mmc/card.h @@ -227,7 +227,7 @@ struct mmc_queue_req; * MMC Physical partitions */ struct mmc_part { - unsigned int size; /* partition size (in bytes) */ + u64 size; /* partition size (in bytes) */ unsigned int part_cfg; /* partition type */ char name[MAX_MMC_PART_NAME_LEN]; bool force_ro; /* to make boot parts RO by default */

From: peter chang dpf@google.com

[ Upstream commit 51c1c5f6ed64c2b65a8cf89dac136273d25ca540 ]

Added the fix so the if driver properly sent the abort it tries to remove it from the firmware's list of outstanding commands regardless of the abort status. This means that the task gets freed 'now' rather than possibly getting freed later when the scsi layer thinks it's leaked but still valid.

Link: https://lore.kernel.org/r/20191114100910.6153-10-deepak.ukey@microchip.com Acked-by: Jack Wang jinpu.wang@cloud.ionos.com Signed-off-by: peter chang dpf@google.com Signed-off-by: Deepak Ukey deepak.ukey@microchip.com Signed-off-by: Viswas G Viswas.G@microchip.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/scsi/pm8001/pm8001_sas.c | 50 +++++++++++++++++++++++--------- 1 file changed, 37 insertions(+), 13 deletions(-)

diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c index ba79b37d8cf7e..5becdde3ea324 100644 --- a/drivers/scsi/pm8001/pm8001_sas.c +++ b/drivers/scsi/pm8001/pm8001_sas.c @@ -1184,8 +1184,8 @@ int pm8001_abort_task(struct sas_task *task) pm8001_ha = pm8001_find_ha_by_dev(dev); device_id = pm8001_dev->device_id; phy_id = pm8001_dev->attached_phy; - rc = pm8001_find_tag(task, &tag); - if (rc == 0) { + ret = pm8001_find_tag(task, &tag); + if (ret == 0) { pm8001_printk("no tag for task:%p\n", task); return TMF_RESP_FUNC_FAILED; } @@ -1223,26 +1223,50 @@ int pm8001_abort_task(struct sas_task *task)

/* 2. Send Phy Control Hard Reset */ reinit_completion(&completion); + phy->port_reset_status = PORT_RESET_TMO; phy->reset_success = false; phy->enable_completion = &completion; phy->reset_completion = &completion_reset; ret = PM8001_CHIP_DISP->phy_ctl_req(pm8001_ha, phy_id, PHY_HARD_RESET); - if (ret) - goto out; - PM8001_MSG_DBG(pm8001_ha, - pm8001_printk("Waiting for local phy ctl\n")); - wait_for_completion(&completion); - if (!phy->reset_success) + if (ret) { + phy->enable_completion = NULL; + phy->reset_completion = NULL; goto out; + }

- /* 3. Wait for Port Reset complete / Port reset TMO */ + /* In the case of the reset timeout/fail we still + * abort the command at the firmware. The assumption + * here is that the drive is off doing something so + * that it's not processing requests, and we want to + * avoid getting a completion for this and either + * leaking the task in libsas or losing the race and + * getting a double free. + */ PM8001_MSG_DBG(pm8001_ha, + pm8001_printk("Waiting for local phy ctl\n")); + ret = wait_for_completion_timeout(&completion, + PM8001_TASK_TIMEOUT * HZ); + if (!ret || !phy->reset_success) { + phy->enable_completion = NULL; + phy->reset_completion = NULL; + } else { + /* 3. Wait for Port Reset complete or + * Port reset TMO + */ + PM8001_MSG_DBG(pm8001_ha, pm8001_printk("Waiting for Port reset\n")); - wait_for_completion(&completion_reset); - if (phy->port_reset_status) { - pm8001_dev_gone_notify(dev); - goto out; + ret = wait_for_completion_timeout( + &completion_reset, + PM8001_TASK_TIMEOUT * HZ); + if (!ret) + phy->reset_completion = NULL; + WARN_ON(phy->port_reset_status == + PORT_RESET_TMO); + if (phy->port_reset_status == PORT_RESET_TMO) { + pm8001_dev_gone_notify(dev); + goto out; + } }

/*

From: Pavel Shilovsky pshilov@microsoft.com

[ Upstream commit 9bd4540836684013aaad6070a65d6fcdd9006625 ]

Currenly we doesn't assume that a server may break a lease from RWH to RW which causes us setting a wrong lease state on a file and thus mistakenly flushing data and byte-range locks and purging cached data on the client. This leads to performance degradation because subsequent IOs go directly to the server.

Fix this by propagating new lease state and epoch values to the oplock break handler through cifsFileInfo structure and removing the use of cifsInodeInfo flags for that. It allows to avoid some races of several lease/oplock breaks using those flags in parallel.

Signed-off-by: Pavel Shilovsky pshilov@microsoft.com Signed-off-by: Steve French stfrench@microsoft.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/cifs/cifsglob.h | 9 ++++++--- fs/cifs/file.c | 10 +++++++--- fs/cifs/misc.c | 17 +++-------------- fs/cifs/smb1ops.c | 8 +++----- fs/cifs/smb2misc.c | 32 +++++++------------------------- fs/cifs/smb2ops.c | 44 ++++++++++++++++++++++++++++++-------------- fs/cifs/smb2pdu.h | 2 +- 7 files changed, 57 insertions(+), 65 deletions(-)

diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h index 71c2dd0c7f038..2c632793c88c5 100644 --- a/fs/cifs/cifsglob.h +++ b/fs/cifs/cifsglob.h @@ -259,8 +259,9 @@ struct smb_version_operations { int (*check_message)(char *, unsigned int, struct TCP_Server_Info *); bool (*is_oplock_break)(char *, struct TCP_Server_Info *); int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *); - void (*downgrade_oplock)(struct TCP_Server_Info *, - struct cifsInodeInfo *, bool); + void (*downgrade_oplock)(struct TCP_Server_Info *server, + struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache); /* process transaction2 response */ bool (*check_trans2)(struct mid_q_entry *, struct TCP_Server_Info *, char *, int); @@ -1160,6 +1161,8 @@ struct cifsFileInfo { unsigned int f_flags; bool invalidHandle:1; /* file closed via session abend */ bool oplock_break_cancelled:1; + unsigned int oplock_epoch; /* epoch from the lease break */ + __u32 oplock_level; /* oplock/lease level from the lease break */ int count; spinlock_t file_info_lock; /* protects four flag/count fields above */ struct mutex fh_mutex; /* prevents reopen race after dead ses*/ @@ -1300,7 +1303,7 @@ struct cifsInodeInfo { unsigned int epoch; /* used to track lease state changes */ #define CIFS_INODE_PENDING_OPLOCK_BREAK (0) /* oplock break in progress */ #define CIFS_INODE_PENDING_WRITERS (1) /* Writes in progress */ -#define CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2 (2) /* Downgrade oplock to L2 */ +#define CIFS_INODE_FLAG_UNUSED (2) /* Unused flag */ #define CIFS_INO_DELETE_PENDING (3) /* delete pending on server */ #define CIFS_INO_INVALID_MAPPING (4) /* pagecache is invalid */ #define CIFS_INO_LOCK (5) /* lock bit for synchronization */ diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 128cbd69911b4..e78b52c582f18 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -4185,12 +4185,13 @@ void cifs_oplock_break(struct work_struct *work) struct cifs_tcon *tcon = tlink_tcon(cfile->tlink); struct TCP_Server_Info *server = tcon->ses->server; int rc = 0; + bool purge_cache = false;

wait_on_bit(&cinode->flags, CIFS_INODE_PENDING_WRITERS, TASK_UNINTERRUPTIBLE);

- server->ops->downgrade_oplock(server, cinode, - test_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, &cinode->flags)); + server->ops->downgrade_oplock(server, cinode, cfile->oplock_level, + cfile->oplock_epoch, &purge_cache);

if (!CIFS_CACHE_WRITE(cinode) && CIFS_CACHE_READ(cinode) && cifs_has_mand_locks(cinode)) { @@ -4205,18 +4206,21 @@ void cifs_oplock_break(struct work_struct *work) else break_lease(inode, O_WRONLY); rc = filemap_fdatawrite(inode->i_mapping); - if (!CIFS_CACHE_READ(cinode)) { + if (!CIFS_CACHE_READ(cinode) || purge_cache) { rc = filemap_fdatawait(inode->i_mapping); mapping_set_error(inode->i_mapping, rc); cifs_zap_mapping(inode); } cifs_dbg(FYI, "Oplock flush inode %p rc %d\n", inode, rc); + if (CIFS_CACHE_WRITE(cinode)) + goto oplock_break_ack; }

rc = cifs_push_locks(cfile); if (rc) cifs_dbg(VFS, "Push locks rc = %d\n", rc);

+oplock_break_ack: /* * releasing stale oplock after recent reconnect of smb session using * a now incorrect file handle is not a data integrity issue but do diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index e45f8e321371c..dd67f56ea61e5 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -477,21 +477,10 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv) set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &pCifsInode->flags);

- /* - * Set flag if the server downgrades the oplock - * to L2 else clear. - */ - if (pSMB->OplockLevel) - set_bit( - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &pCifsInode->flags); - else - clear_bit( - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &pCifsInode->flags); - - cifs_queue_oplock_break(netfile); + netfile->oplock_epoch = 0; + netfile->oplock_level = pSMB->OplockLevel; netfile->oplock_break_cancelled = false; + cifs_queue_oplock_break(netfile);

spin_unlock(&tcon->open_file_lock); spin_unlock(&cifs_tcp_ses_lock); diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c index c7f0c85664425..0b7f924512848 100644 --- a/fs/cifs/smb1ops.c +++ b/fs/cifs/smb1ops.c @@ -381,12 +381,10 @@ coalesce_t2(char *second_buf, struct smb_hdr *target_hdr)

static void cifs_downgrade_oplock(struct TCP_Server_Info *server, - struct cifsInodeInfo *cinode, bool set_level2) + struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache) { - if (set_level2) - cifs_set_oplock_level(cinode, OPLOCK_READ); - else - cifs_set_oplock_level(cinode, 0); + cifs_set_oplock_level(cinode, oplock); }

static bool diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c index 2fc96f7923ee5..7d875a47d0226 100644 --- a/fs/cifs/smb2misc.c +++ b/fs/cifs/smb2misc.c @@ -550,7 +550,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp)

cifs_dbg(FYI, "found in the open list\n"); cifs_dbg(FYI, "lease key match, lease break 0x%x\n", - le32_to_cpu(rsp->NewLeaseState)); + lease_state);

if (ack_req) cfile->oplock_break_cancelled = false; @@ -559,17 +559,8 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp)

set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags);

- /* - * Set or clear flags depending on the lease state being READ. - * HANDLE caching flag should be added when the client starts - * to defer closing remote file handles with HANDLE leases. - */ - if (lease_state & SMB2_LEASE_READ_CACHING_HE) - set_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); - else - clear_bit(CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); + cfile->oplock_epoch = le16_to_cpu(rsp->Epoch); + cfile->oplock_level = lease_state;

cifs_queue_oplock_break(cfile); return true; @@ -599,7 +590,7 @@ smb2_tcon_find_pending_open_lease(struct cifs_tcon *tcon,

cifs_dbg(FYI, "found in the pending open list\n"); cifs_dbg(FYI, "lease key match, lease break 0x%x\n", - le32_to_cpu(rsp->NewLeaseState)); + lease_state);

open->oplock = lease_state; } @@ -732,18 +723,9 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server) set_bit(CIFS_INODE_PENDING_OPLOCK_BREAK, &cinode->flags);

- /* - * Set flag if the server downgrades the oplock - * to L2 else clear. - */ - if (rsp->OplockLevel) - set_bit( - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); - else - clear_bit( - CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2, - &cinode->flags); + cfile->oplock_epoch = 0; + cfile->oplock_level = rsp->OplockLevel; + spin_unlock(&cfile->file_info_lock);

cifs_queue_oplock_break(cfile); diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 2a523139a05fb..947a40069d246 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2358,22 +2358,38 @@ static long smb3_fallocate(struct file *file, struct cifs_tcon *tcon, int mode,

static void smb2_downgrade_oplock(struct TCP_Server_Info *server, - struct cifsInodeInfo *cinode, bool set_level2) + struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache) { - if (set_level2) - server->ops->set_oplock_level(cinode, SMB2_OPLOCK_LEVEL_II, - 0, NULL); - else - server->ops->set_oplock_level(cinode, 0, 0, NULL); + server->ops->set_oplock_level(cinode, oplock, 0, NULL); }

static void -smb21_downgrade_oplock(struct TCP_Server_Info *server, - struct cifsInodeInfo *cinode, bool set_level2) +smb21_set_oplock_level(struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache); + +static void +smb3_downgrade_oplock(struct TCP_Server_Info *server, + struct cifsInodeInfo *cinode, __u32 oplock, + unsigned int epoch, bool *purge_cache) { - server->ops->set_oplock_level(cinode, - set_level2 ? SMB2_LEASE_READ_CACHING_HE : - 0, 0, NULL); + unsigned int old_state = cinode->oplock; + unsigned int old_epoch = cinode->epoch; + unsigned int new_state; + + if (epoch > old_epoch) { + smb21_set_oplock_level(cinode, oplock, 0, NULL); + cinode->epoch = epoch; + } + + new_state = cinode->oplock; + *purge_cache = false; + + if ((old_state & CIFS_CACHE_READ_FLG) != 0 && + (new_state & CIFS_CACHE_READ_FLG) == 0) + *purge_cache = true; + else if (old_state == new_state && (epoch - old_epoch > 1)) + *purge_cache = true; }

static void @@ -3449,7 +3465,7 @@ struct smb_version_operations smb21_operations = { .print_stats = smb2_print_stats, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb21_downgrade_oplock, + .downgrade_oplock = smb2_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, @@ -3546,7 +3562,7 @@ struct smb_version_operations smb30_operations = { .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb21_downgrade_oplock, + .downgrade_oplock = smb3_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, @@ -3651,7 +3667,7 @@ struct smb_version_operations smb311_operations = { .dump_share_caps = smb2_dump_share_caps, .is_oplock_break = smb2_is_valid_oplock_break, .handle_cancelled_mid = smb2_handle_cancelled_mid, - .downgrade_oplock = smb21_downgrade_oplock, + .downgrade_oplock = smb3_downgrade_oplock, .need_neg = smb2_need_neg, .negotiate = smb2_negotiate, .negotiate_wsize = smb2_negotiate_wsize, diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h index 308c682fa4d3b..44501f8cbd75e 100644 --- a/fs/cifs/smb2pdu.h +++ b/fs/cifs/smb2pdu.h @@ -1209,7 +1209,7 @@ struct smb2_oplock_break { struct smb2_lease_break { struct smb2_sync_hdr sync_hdr; __le16 StructureSize; /* Must be 44 */ - __le16 Reserved; + __le16 Epoch; __le32 Flags; __u8 LeaseKey[16]; __le32 CurrentLeaseState;

From: Joe Perches joe@perches.com

[ Upstream commit 5e1aada08cd19ea652b2d32a250501d09b02ff2e ]

Initialization is not guaranteed to zero padding bytes so use an explicit memset instead to avoid leaking any kernel content in any possible padding bytes.

Link: http://lkml.kernel.org/r/dfa331c00881d61c8ee51577a082d8bebd61805c.camel@perc... Signed-off-by: Joe Perches joe@perches.com Cc: Dan Carpenter error27@gmail.com Cc: Julia Lawall julia.lawall@lip6.fr Cc: Thomas Gleixner tglx@linutronix.de Cc: Kees Cook keescook@chromium.org 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 --- kernel/sys.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/kernel/sys.c b/kernel/sys.c index 096932a450466..baf60a3aa34b7 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1275,11 +1275,13 @@ SYSCALL_DEFINE1(uname, struct old_utsname __user *, name)

SYSCALL_DEFINE1(olduname, struct oldold_utsname __user *, name) { - struct oldold_utsname tmp = {}; + struct oldold_utsname tmp;

if (!name) return -EFAULT;

+ memset(&tmp, 0, sizeof(tmp)); + down_read(&uts_sem); memcpy(&tmp.sysname, &utsname()->sysname, __OLD_UTS_LEN); memcpy(&tmp.nodename, &utsname()->nodename, __OLD_UTS_LEN);

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

[ Upstream commit b1de6fc7520fe12949c070af0e8c0e4044cd3420 ]

Omar Sandoval reported that a 4G fallocate on the realtime device causes filesystem shutdowns due to a log reservation overflow that happens when we log the rtbitmap updates. Factor rtbitmap/rtsummary updates into the the tr_write and tr_itruncate log reservation calculation.

"The following reproducer results in a transaction log overrun warning for me:

mkfs.xfs -f -r rtdev=/dev/vdc -d rtinherit=1 -m reflink=0 /dev/vdb mount -o rtdev=/dev/vdc /dev/vdb /mnt fallocate -l 4G /mnt/foo

Reported-by: Omar Sandoval osandov@osandov.com Tested-by: Omar Sandoval osandov@osandov.com Signed-off-by: Darrick J. Wong darrick.wong@oracle.com Reviewed-by: Brian Foster bfoster@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- fs/xfs/libxfs/xfs_trans_resv.c | 96 +++++++++++++++++++++++++++------- 1 file changed, 77 insertions(+), 19 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c index f99a7aefe4184..2b3cc5a8ced1b 100644 --- a/fs/xfs/libxfs/xfs_trans_resv.c +++ b/fs/xfs/libxfs/xfs_trans_resv.c @@ -197,6 +197,24 @@ xfs_calc_inode_chunk_res( return res; }

+/* + * Per-extent log reservation for the btree changes involved in freeing or + * allocating a realtime extent. We have to be able to log as many rtbitmap + * blocks as needed to mark inuse MAXEXTLEN blocks' worth of realtime extents, + * as well as the realtime summary block. + */ +unsigned int +xfs_rtalloc_log_count( + struct xfs_mount *mp, + unsigned int num_ops) +{ + unsigned int blksz = XFS_FSB_TO_B(mp, 1); + unsigned int rtbmp_bytes; + + rtbmp_bytes = (MAXEXTLEN / mp->m_sb.sb_rextsize) / NBBY; + return (howmany(rtbmp_bytes, blksz) + 1) * num_ops; +} + /* * Various log reservation values. * @@ -219,13 +237,21 @@ xfs_calc_inode_chunk_res(

/* * In a write transaction we can allocate a maximum of 2 - * extents. This gives: + * extents. This gives (t1): * the inode getting the new extents: inode size * the inode's bmap btree: max depth * block size * the agfs of the ags from which the extents are allocated: 2 * sector * the superblock free block counter: sector size * the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size - * And the bmap_finish transaction can free bmap blocks in a join: + * Or, if we're writing to a realtime file (t2): + * the inode getting the new extents: inode size + * the inode's bmap btree: max depth * block size + * the agfs of the ags from which the extents are allocated: 2 * sector + * the superblock free block counter: sector size + * the realtime bitmap: ((MAXEXTLEN / rtextsize) / NBBY) bytes + * the realtime summary: 1 block + * the allocation btrees: 2 trees * (2 * max depth - 1) * block size + * And the bmap_finish transaction can free bmap blocks in a join (t3): * the agfs of the ags containing the blocks: 2 * sector size * the agfls of the ags containing the blocks: 2 * sector size * the super block free block counter: sector size @@ -235,40 +261,72 @@ STATIC uint xfs_calc_write_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + - max((xfs_calc_inode_res(mp, 1) + + unsigned int t1, t2, t3; + unsigned int blksz = XFS_FSB_TO_B(mp, 1); + + t1 = xfs_calc_inode_res(mp, 1) + + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), blksz) + + xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz); + + if (xfs_sb_version_hasrealtime(&mp->m_sb)) { + t2 = xfs_calc_inode_res(mp, 1) + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK), - XFS_FSB_TO_B(mp, 1)) + + blksz) + xfs_calc_buf_res(3, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), - XFS_FSB_TO_B(mp, 1))), - (xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), - XFS_FSB_TO_B(mp, 1)))); + xfs_calc_buf_res(xfs_rtalloc_log_count(mp, 1), blksz) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 1), blksz); + } else { + t2 = 0; + } + + t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz); + + return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); }

/* - * In truncating a file we free up to two extents at once. We can modify: + * In truncating a file we free up to two extents at once. We can modify (t1): * the inode being truncated: inode size * the inode's bmap btree: (max depth + 1) * block size - * And the bmap_finish transaction can free the blocks and bmap blocks: + * And the bmap_finish transaction can free the blocks and bmap blocks (t2): * the agf for each of the ags: 4 * sector size * the agfl for each of the ags: 4 * sector size * the super block to reflect the freed blocks: sector size * worst case split in allocation btrees per extent assuming 4 extents: * 4 exts * 2 trees * (2 * max depth - 1) * block size + * Or, if it's a realtime file (t3): + * the agf for each of the ags: 2 * sector size + * the agfl for each of the ags: 2 * sector size + * the super block to reflect the freed blocks: sector size + * the realtime bitmap: 2 exts * ((MAXEXTLEN / rtextsize) / NBBY) bytes + * the realtime summary: 2 exts * 1 block + * worst case split in allocation btrees per extent assuming 2 extents: + * 2 exts * 2 trees * (2 * max depth - 1) * block size */ STATIC uint xfs_calc_itruncate_reservation( struct xfs_mount *mp) { - return XFS_DQUOT_LOGRES(mp) + - max((xfs_calc_inode_res(mp, 1) + - xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, - XFS_FSB_TO_B(mp, 1))), - (xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) + - xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4), - XFS_FSB_TO_B(mp, 1)))); + unsigned int t1, t2, t3; + unsigned int blksz = XFS_FSB_TO_B(mp, 1); + + t1 = xfs_calc_inode_res(mp, 1) + + xfs_calc_buf_res(XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) + 1, blksz); + + t2 = xfs_calc_buf_res(9, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 4), blksz); + + if (xfs_sb_version_hasrealtime(&mp->m_sb)) { + t3 = xfs_calc_buf_res(5, mp->m_sb.sb_sectsize) + + xfs_calc_buf_res(xfs_rtalloc_log_count(mp, 2), blksz) + + xfs_calc_buf_res(xfs_allocfree_log_count(mp, 2), blksz); + } else { + t3 = 0; + } + + return XFS_DQUOT_LOGRES(mp) + max3(t1, t2, t3); }

/*

From: Vasily Averin vvs@virtuozzo.com

[ Upstream commit a3ea86739f1bc7e121d921842f0f4a8ab1af94d9 ]

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 --- net/ipv4/route.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 84de87b7eedcd..3db428242b22d 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -274,6 +274,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } + (*pos)++; return NULL;

}

From: Marco Elver elver@google.com

[ Upstream commit bf07132f96d426bcbf2098227fb680915cf44498 ]

This patch proposes to require marked atomic accesses surrounding raw_write_seqcount_barrier. We reason that otherwise there is no way to guarantee propagation nor atomicity of writes before/after the barrier [1]. For example, consider the compiler tears stores either before or after the barrier; in this case, readers may observe a partial value, and because readers are unaware that writes are going on (writes are not in a seq-writer critical section), will complete the seq-reader critical section while having observed some partial state. [1] https://lwn.net/Articles/793253/

This came up when designing and implementing KCSAN, because KCSAN would flag these accesses as data-races. After careful analysis, our reasoning as above led us to conclude that the best thing to do is to propose an amendment to the raw_seqcount_barrier usage.

Signed-off-by: Marco Elver elver@google.com Acked-by: Paul E. McKenney paulmck@kernel.org Signed-off-by: Paul E. McKenney paulmck@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- include/linux/seqlock.h | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index bcf4cf26b8c89..a42a29952889c 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -243,6 +243,13 @@ static inline void raw_write_seqcount_end(seqcount_t *s) * usual consistency guarantee. It is one wmb cheaper, because we can * collapse the two back-to-back wmb()s. * + * Note that, writes surrounding the barrier should be declared atomic (e.g. + * via WRITE_ONCE): a) to ensure the writes become visible to other threads + * atomically, avoiding compiler optimizations; b) to document which writes are + * meant to propagate to the reader critical section. This is necessary because + * neither writes before and after the barrier are enclosed in a seq-writer + * critical section that would ensure readers are aware of ongoing writes. + * * seqcount_t seq; * bool X = true, Y = false; * @@ -262,11 +269,11 @@ static inline void raw_write_seqcount_end(seqcount_t *s) * * void write(void) * { - * Y = true; + * WRITE_ONCE(Y, true); * * raw_write_seqcount_barrier(seq); * - * X = false; + * WRITE_ONCE(X, false); * } */ static inline void raw_write_seqcount_barrier(seqcount_t *s)

From: Kevin Kou qdkevin.kou@gmail.com

[ Upstream commit f643ee295c1c63bc117fb052d4da681354d6f732 ]

The original patch bringed in the "SCTP ACK tracking trace event" feature was committed at Dec.20, 2017, it replaced jprobe usage with trace events, and bringed in two trace events, one is TRACE_EVENT(sctp_probe), another one is TRACE_EVENT(sctp_probe_path). The original patch intended to trigger the trace_sctp_probe_path in TRACE_EVENT(sctp_probe) as below code,

+TRACE_EVENT(sctp_probe, + + TP_PROTO(const struct sctp_endpoint *ep, + const struct sctp_association *asoc, + struct sctp_chunk *chunk), + + TP_ARGS(ep, asoc, chunk), + + TP_STRUCT__entry( + __field(__u64, asoc) + __field(__u32, mark) + __field(__u16, bind_port) + __field(__u16, peer_port) + __field(__u32, pathmtu) + __field(__u32, rwnd) + __field(__u16, unack_data) + ), + + TP_fast_assign( + struct sk_buff *skb = chunk->skb; + + __entry->asoc = (unsigned long)asoc; + __entry->mark = skb->mark; + __entry->bind_port = ep->base.bind_addr.port; + __entry->peer_port = asoc->peer.port; + __entry->pathmtu = asoc->pathmtu; + __entry->rwnd = asoc->peer.rwnd; + __entry->unack_data = asoc->unack_data; + + if (trace_sctp_probe_path_enabled()) { + struct sctp_transport *sp; + + list_for_each_entry(sp, &asoc->peer.transport_addr_list, + transports) { + trace_sctp_probe_path(sp, asoc); + } + } + ),

But I found it did not work when I did testing, and trace_sctp_probe_path had no output, I finally found that there is trace buffer lock operation(trace_event_buffer_reserve) in include/trace/trace_events.h:

static notrace void \ trace_event_raw_event_##call(void *__data, proto) \ { \ struct trace_event_file *trace_file = __data; \ struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\ struct trace_event_buffer fbuffer; \ struct trace_event_raw_##call *entry; \ int __data_size; \ \ if (trace_trigger_soft_disabled(trace_file)) \ return; \ \ __data_size = trace_event_get_offsets_##call(&__data_offsets, args); \ \ entry = trace_event_buffer_reserve(&fbuffer, trace_file, \ sizeof(*entry) + __data_size); \ \ if (!entry) \ return; \ \ tstruct \ \ { assign; } \ \ trace_event_buffer_commit(&fbuffer); \ }

The reason caused no output of trace_sctp_probe_path is that trace_sctp_probe_path written in TP_fast_assign part of TRACE_EVENT(sctp_probe), and it will be placed( { assign; } ) after the trace_event_buffer_reserve() when compiler expands Macro,

entry = trace_event_buffer_reserve(&fbuffer, trace_file, \ sizeof(*entry) + __data_size); \ \ if (!entry) \ return; \ \ tstruct \ \ { assign; } \

so trace_sctp_probe_path finally can not acquire trace_event_buffer and return no output, that is to say the nest of tracepoint entry function is not allowed. The function call flow is:

trace_sctp_probe() -> trace_event_raw_event_sctp_probe() -> lock buffer -> trace_sctp_probe_path() -> trace_event_raw_event_sctp_probe_path() --nested -> buffer has been locked and return no output.

This patch is to remove trace_sctp_probe_path from the TP_fast_assign part of TRACE_EVENT(sctp_probe) to avoid the nest of entry function, and trigger sctp_probe_path_trace in sctp_outq_sack.

After this patch, you can enable both events individually, # cd /sys/kernel/debug/tracing # echo 1 > events/sctp/sctp_probe/enable # echo 1 > events/sctp/sctp_probe_path/enable

Or, you can enable all the events under sctp.

# echo 1 > events/sctp/enable

Signed-off-by: Kevin Kou qdkevin.kou@gmail.com Acked-by: Marcelo Ricardo Leitner marcelo.leitner@gmail.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- include/trace/events/sctp.h | 9 --------- net/sctp/outqueue.c | 6 ++++++ 2 files changed, 6 insertions(+), 9 deletions(-)

diff --git a/include/trace/events/sctp.h b/include/trace/events/sctp.h index 7475c7be165aa..d4aac34365955 100644 --- a/include/trace/events/sctp.h +++ b/include/trace/events/sctp.h @@ -75,15 +75,6 @@ TRACE_EVENT(sctp_probe, __entry->pathmtu = asoc->pathmtu; __entry->rwnd = asoc->peer.rwnd; __entry->unack_data = asoc->unack_data; - - if (trace_sctp_probe_path_enabled()) { - struct sctp_transport *sp; - - list_for_each_entry(sp, &asoc->peer.transport_addr_list, - transports) { - trace_sctp_probe_path(sp, asoc); - } - } ),

TP_printk("asoc=%#llx mark=%#x bind_port=%d peer_port=%d pathmtu=%d " diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 7bb8e5603298d..d6e83a37a1adf 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -51,6 +51,7 @@ #include <net/sctp/sctp.h> #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> +#include <trace/events/sctp.h>

/* Declare internal functions here. */ static int sctp_acked(struct sctp_sackhdr *sack, __u32 tsn); @@ -1257,6 +1258,11 @@ int sctp_outq_sack(struct sctp_outq *q, struct sctp_chunk *chunk) /* Grab the association's destination address list. */ transport_list = &asoc->peer.transport_addr_list;

+ /* SCTP path tracepoint for congestion control debugging. */ + list_for_each_entry(transport, transport_list, transports) { + trace_sctp_probe_path(transport, asoc); + } + sack_ctsn = ntohl(sack->cum_tsn_ack); gap_ack_blocks = ntohs(sack->num_gap_ack_blocks); asoc->stats.gapcnt += gap_ack_blocks;

From: Bart Van Assche bvanassche@acm.org

[ Upstream commit e4d2add7fd5bc64ee3e388eabe6b9e081cb42e11 ]

Since the lrbp->cmd expression occurs multiple times, introduce a new local variable to hold that pointer. This patch does not change any functionality.

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/20191224220248.30138-3-bvanassche@acm.org Reviewed-by: Stanley Chu stanley.chu@mediatek.com Reviewed-by: Can Guo cang@codeaurora.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 --- drivers/scsi/ufs/ufshcd.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index eb10a5cacd90c..faf1959981784 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -353,27 +353,27 @@ static void ufshcd_add_command_trace(struct ufs_hba *hba, u8 opcode = 0; u32 intr, doorbell; struct ufshcd_lrb *lrbp = &hba->lrb[tag]; + struct scsi_cmnd *cmd = lrbp->cmd; int transfer_len = -1;

if (!trace_ufshcd_command_enabled()) { /* trace UPIU W/O tracing command */ - if (lrbp->cmd) + if (cmd) ufshcd_add_cmd_upiu_trace(hba, tag, str); return; }

- if (lrbp->cmd) { /* data phase exists */ + if (cmd) { /* data phase exists */ /* trace UPIU also */ ufshcd_add_cmd_upiu_trace(hba, tag, str); - opcode = (u8)(*lrbp->cmd->cmnd); + opcode = cmd->cmnd[0]; if ((opcode == READ_10) || (opcode == WRITE_10)) { /* * Currently we only fully trace read(10) and write(10) * commands */ - if (lrbp->cmd->request && lrbp->cmd->request->bio) - lba = - lrbp->cmd->request->bio->bi_iter.bi_sector; + if (cmd->request && cmd->request->bio) + lba = cmd->request->bio->bi_iter.bi_sector; transfer_len = be32_to_cpu( lrbp->ucd_req_ptr->sc.exp_data_transfer_len); }

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 --- 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 faf1959981784..b2cbdd01ab10b 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 --- 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 74a296cea21cc..0e6d01225a670 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 --- 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 8d1cd2479e36f..cc51395d8b0e5 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 --- 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 a4d4a28fe07df..d23ab9ec130a3 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 badf02ca36938..aec533168f046 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 --- 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 1e438e0faf77e..3c24fb77ef325 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 --- .../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 2fa3c5757bcb5..dbed3d213bf17 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 --- mm/swapfile.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c index 0047dcaf93697..c3684cfa9534e 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2738,10 +2738,10 @@ 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: Hillf Danton hdanton@sina.com

[ Upstream commit 2a154903cec20fb64ff4d7d617ca53c16f8fd53a ]

Prefetch channel before killing sock in order to fix UAF like

BUG: KASAN: use-after-free in l2cap_sock_release+0x24c/0x290 net/bluetooth/l2cap_sock.c:1212 Read of size 8 at addr ffff8880944904a0 by task syz-fuzzer/9751

Reported-by: syzbot+c3c5bdea7863886115dc@syzkaller.appspotmail.com Fixes: 6c08fc896b60 ("Bluetooth: Fix refcount use-after-free issue") Cc: Manish Mandlik mmandlik@google.com Signed-off-by: Hillf Danton hdanton@sina.com Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/l2cap_sock.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index d128750e47305..5572042f04531 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -1190,6 +1190,7 @@ static int l2cap_sock_release(struct socket *sock) { struct sock *sk = sock->sk; int err; + struct l2cap_chan *chan;

BT_DBG("sock %p, sk %p", sock, sk);

@@ -1199,15 +1200,16 @@ static int l2cap_sock_release(struct socket *sock) bt_sock_unlink(&l2cap_sk_list, sk);

err = l2cap_sock_shutdown(sock, 2); + chan = l2cap_pi(sk)->chan;

- l2cap_chan_hold(l2cap_pi(sk)->chan); - l2cap_chan_lock(l2cap_pi(sk)->chan); + l2cap_chan_hold(chan); + l2cap_chan_lock(chan);

sock_orphan(sk); l2cap_sock_kill(sk);

- l2cap_chan_unlock(l2cap_pi(sk)->chan); - l2cap_chan_put(l2cap_pi(sk)->chan); + l2cap_chan_unlock(chan); + l2cap_chan_put(chan);

return err; }

From: Mohan Kumar mkumard@nvidia.com

[ Upstream commit 6d011d5057ff88ee556c000ac6fe0be23bdfcd72 ]

RIRB interrupt status getting cleared after the write pointer is read causes a race condition, where last response(s) into RIRB may remain unserviced by IRQ, eventually causing azx_rirb_get_response to fall back to polling mode. Clearing the RIRB interrupt status ahead of write pointer access ensures that this condition is avoided.

Signed-off-by: Mohan Kumar mkumard@nvidia.com Signed-off-by: Viswanath L viswanathl@nvidia.com Link: https://lore.kernel.org/r/1580983853-351-1-git-send-email-viswanathl@nvidia.... Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/pci/hda/hda_controller.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/sound/pci/hda/hda_controller.c b/sound/pci/hda/hda_controller.c index fa261b27d8588..8198d2e53b7df 100644 --- a/sound/pci/hda/hda_controller.c +++ b/sound/pci/hda/hda_controller.c @@ -1169,16 +1169,23 @@ irqreturn_t azx_interrupt(int irq, void *dev_id) if (snd_hdac_bus_handle_stream_irq(bus, status, stream_update)) active = true;

- /* clear rirb int */ status = azx_readb(chip, RIRBSTS); if (status & RIRB_INT_MASK) { + /* + * Clearing the interrupt status here ensures that no + * interrupt gets masked after the RIRB wp is read in + * snd_hdac_bus_update_rirb. This avoids a possible + * race condition where codec response in RIRB may + * remain unserviced by IRQ, eventually falling back + * to polling mode in azx_rirb_get_response. + */ + azx_writeb(chip, RIRBSTS, RIRB_INT_MASK); active = true; if (status & RIRB_INT_RESPONSE) { if (chip->driver_caps & AZX_DCAPS_CTX_WORKAROUND) udelay(80); snd_hdac_bus_update_rirb(bus); } - azx_writeb(chip, RIRBSTS, RIRB_INT_MASK); } } while (active && ++repeat < 10);

From: Steve Grubb sgrubb@redhat.com

[ Upstream commit 70b3eeed49e8190d97139806f6fbaf8964306cdb ]

Common Criteria calls out for any action that modifies the audit trail to be recorded. That usually is interpreted to mean insertion or removal of rules. It is not required to log modification of the inode information since the watch is still in effect. Additionally, if the rule is a never rule and the underlying file is one they do not want events for, they get an event for this bookkeeping update against their wishes.

Since no device/inode info is logged at insertion and no device/inode information is logged on update, there is nothing meaningful being communicated to the admin by the CONFIG_CHANGE updated_rules event. One can assume that the rule was not "modified" because it is still watching the intended target. If the device or inode cannot be resolved, then audit_panic is called which is sufficient.

The correct resolution is to drop logging config_update events since the watch is still in effect but just on another unknown inode.

Signed-off-by: Steve Grubb sgrubb@redhat.com Signed-off-by: Paul Moore paul@paul-moore.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/audit_watch.c | 2 -- 1 file changed, 2 deletions(-)

diff --git a/kernel/audit_watch.c b/kernel/audit_watch.c index 4f7262eba73d8..50952d6d81209 100644 --- a/kernel/audit_watch.c +++ b/kernel/audit_watch.c @@ -317,8 +317,6 @@ static void audit_update_watch(struct audit_parent *parent, if (oentry->rule.exe) audit_remove_mark(oentry->rule.exe);

- audit_watch_log_rule_change(r, owatch, "updated_rules"); - call_rcu(&oentry->rcu, audit_free_rule_rcu); }

From: James Smart jsmart2021@gmail.com

[ Upstream commit 39c4f1a965a9244c3ba60695e8ff8da065ec6ac4 ]

The driver is occasionally seeing the following SLI Port error, requiring reset and reinit:

Port Status Event: ... error 1=0x52004a01, error 2=0x218

The failure means an RQ timeout. That is, the adapter had received asynchronous receive frames, ran out of buffer slots to place the frames, and the driver did not replenish the buffer slots before a timeout occurred. The driver should not be so slow in replenishing buffers that a timeout can occur.

When the driver received all the frames of a sequence, it allocates an IOCB to put the frames in. In a situation where there was no IOCB available for the frame of a sequence, the RQ buffer corresponding to the first frame of the sequence was not returned to the FW. Eventually, with enough traffic encountering the situation, the timeout occurred.

Fix by releasing the buffer back to firmware whenever there is no IOCB for the first frame.

[mkp: typo]

Link: https://lore.kernel.org/r/20200128002312.16346-2-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 --- drivers/scsi/lpfc/lpfc_sli.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c index a56a939792ac1..2ab351260e815 100644 --- a/drivers/scsi/lpfc/lpfc_sli.c +++ b/drivers/scsi/lpfc/lpfc_sli.c @@ -17413,6 +17413,10 @@ lpfc_prep_seq(struct lpfc_vport *vport, struct hbq_dmabuf *seq_dmabuf) list_add_tail(&iocbq->list, &first_iocbq->list); } } + /* Free the sequence's header buffer */ + if (!first_iocbq) + lpfc_in_buf_free(vport->phba, &seq_dmabuf->dbuf); + return first_iocbq; }

From: Wen Yang wen.yang99@zte.com.cn

[ Upstream commit 47340e46f34a3b1d80e40b43ae3d7a8da34a3541 ]

The call to of_find_matching_node returns a node pointer with refcount incremented thus it must be explicitly decremented after the last usage.

Detected by coccinelle with the following warnings: drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c:212:2-8: ERROR: missing of_node_put; acquired a node pointer with refcount incremented on line 209, but without a corresponding object release within this function. drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c:237:1-7: ERROR: missing of_node_put; acquired a node pointer with refcount incremented on line 209, but without a corresponding object release within this function.

Signed-off-by: Wen Yang wen.yang99@zte.com.cn Reviewed-by: Laurent Pinchart laurent.pinchart@ideasonboard.com Reviewed-by: Mukesh Ojha mojha@codeaurora.org Cc: Tomi Valkeinen tomi.valkeinen@ti.com Cc: David Airlie airlied@linux.ie Cc: Daniel Vetter daniel@ffwll.ch Cc: Sebastian Reichel sebastian.reichel@collabora.com Cc: Laurent Pinchart laurent.pinchart@ideasonboard.com Cc: dri-devel@lists.freedesktop.org Cc: linux-kernel@vger.kernel.org Cc: Markus Elfring Markus.Elfring@web.de Signed-off-by: Tomi Valkeinen tomi.valkeinen@ti.com Link: https://patchwork.freedesktop.org/patch/msgid/1554692313-28882-2-git-send-em... Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c b/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c index 3bfb95d230e0e..d8fb686c1fda9 100644 --- a/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c +++ b/drivers/gpu/drm/omapdrm/dss/omapdss-boot-init.c @@ -193,7 +193,7 @@ static int __init omapdss_boot_init(void) dss = of_find_matching_node(NULL, omapdss_of_match);

if (dss == NULL || !of_device_is_available(dss)) - return 0; + goto put_node;

omapdss_walk_device(dss, true);

@@ -218,6 +218,8 @@ static int __init omapdss_boot_init(void) kfree(n); }

+put_node: + of_node_put(dss); return 0; }

From: Ayush Sawal ayush.sawal@chelsio.com

[ Upstream commit 9195189e00a7db55e7d448cee973cae87c5a3c71 ]

The libkcapi test which causes kernel panic is aead asynchronous vmsplice multiple test.

./bin/kcapi -v -d 4 -x 10 -c "ccm(aes)" -q 4edb58e8d5eb6bc711c43a6f3693daebde2e5524f1b55297abb29f003236e43d -t a7877c99 -n 674742abd0f5ba -k 2861fd0253705d7875c95ba8a53171b4 -a fb7bc304a3909e66e2e0c5ef952712dd884ce3e7324171369f2c5db1adc48c7d

This patch avoids dma_mapping of a zero length sg which causes the panic, by using sg_nents_for_len which maps only upto a specific length

Signed-off-by: Ayush Sawal ayush.sawal@chelsio.com Signed-off-by: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/crypto/chelsio/chcr_algo.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/crypto/chelsio/chcr_algo.c b/drivers/crypto/chelsio/chcr_algo.c index 9b3c259f081d3..ee508bbbb7504 100644 --- a/drivers/crypto/chelsio/chcr_algo.c +++ b/drivers/crypto/chelsio/chcr_algo.c @@ -2418,8 +2418,9 @@ int chcr_aead_dma_map(struct device *dev, else reqctx->b0_dma = 0; if (req->src == req->dst) { - error = dma_map_sg(dev, req->src, sg_nents(req->src), - DMA_BIDIRECTIONAL); + error = dma_map_sg(dev, req->src, + sg_nents_for_len(req->src, dst_size), + DMA_BIDIRECTIONAL); if (!error) goto err; } else {

From: Takashi Iwai tiwai@suse.de

[ Upstream commit e9a0ef0b5ddcbc0d56c65aefc0f18d16e6f71207 ]

Some USB-audio descriptors provide a bogus volume range (e.g. volume min and max are identical), which confuses user-space. This patch makes the driver skipping such a control element.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=206221 Link: https://lore.kernel.org/r/20200214144928.23628-1-tiwai@suse.de Signed-off-by: Takashi Iwai tiwai@suse.de Signed-off-by: Sasha Levin sashal@kernel.org --- sound/usb/mixer.c | 10 ++++++++++ 1 file changed, 10 insertions(+)

diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index 45bd3d54be54b..451b8ea383c61 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -1699,6 +1699,16 @@ static void __build_feature_ctl(struct usb_mixer_interface *mixer, /* get min/max values */ get_min_max_with_quirks(cval, 0, kctl);

+ /* skip a bogus volume range */ + if (cval->max <= cval->min) { + usb_audio_dbg(mixer->chip, + "[%d] FU [%s] skipped due to invalid volume\n", + cval->head.id, kctl->id.name); + snd_ctl_free_one(kctl); + return; + } + + if (control == UAC_FU_VOLUME) { check_mapped_dB(map, cval); if (cval->dBmin < cval->dBmax || !cval->initialized) {

From: Bart Van Assche bvanassche@acm.org

[ Upstream commit fb3063d31995cc4cf1d47a406bb61d6fb1b1d58d ]

From the comment above the definition of the roundup_pow_of_two() macro:

The result is undefined when n == 0.

Hence only pass positive values to roundup_pow_of_two(). This patch fixes the following UBSAN complaint:

UBSAN: Undefined behaviour in ./include/linux/log2.h:57:13 shift exponent 64 is too large for 64-bit type 'long unsigned int' Call Trace: dump_stack+0xa5/0xe6 ubsan_epilogue+0x9/0x26 __ubsan_handle_shift_out_of_bounds.cold+0x4c/0xf9 rxe_qp_from_attr.cold+0x37/0x5d [rdma_rxe] rxe_modify_qp+0x59/0x70 [rdma_rxe] _ib_modify_qp+0x5aa/0x7c0 [ib_core] ib_modify_qp+0x3b/0x50 [ib_core] cma_modify_qp_rtr+0x234/0x260 [rdma_cm] __rdma_accept+0x1a7/0x650 [rdma_cm] nvmet_rdma_cm_handler+0x1286/0x14cd [nvmet_rdma] cma_cm_event_handler+0x6b/0x330 [rdma_cm] cma_ib_req_handler+0xe60/0x22d0 [rdma_cm] cm_process_work+0x30/0x140 [ib_cm] cm_req_handler+0x11f4/0x1cd0 [ib_cm] cm_work_handler+0xb8/0x344e [ib_cm] process_one_work+0x569/0xb60 worker_thread+0x7a/0x5d0 kthread+0x1e6/0x210 ret_from_fork+0x24/0x30

Link: https://lore.kernel.org/r/20200217205714.26937-1-bvanassche@acm.org Fixes: 8700e3e7c485 ("Soft RoCE driver") Signed-off-by: Bart Van Assche bvanassche@acm.org Reviewed-by: Leon Romanovsky leonro@mellanox.com Signed-off-by: Jason Gunthorpe jgg@mellanox.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/infiniband/sw/rxe/rxe_qp.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/infiniband/sw/rxe/rxe_qp.c b/drivers/infiniband/sw/rxe/rxe_qp.c index 230697fa31fe3..8a22ab8b29e9b 100644 --- a/drivers/infiniband/sw/rxe/rxe_qp.c +++ b/drivers/infiniband/sw/rxe/rxe_qp.c @@ -583,15 +583,16 @@ int rxe_qp_from_attr(struct rxe_qp *qp, struct ib_qp_attr *attr, int mask, int err;

if (mask & IB_QP_MAX_QP_RD_ATOMIC) { - int max_rd_atomic = __roundup_pow_of_two(attr->max_rd_atomic); + int max_rd_atomic = attr->max_rd_atomic ? + roundup_pow_of_two(attr->max_rd_atomic) : 0;

qp->attr.max_rd_atomic = max_rd_atomic; atomic_set(&qp->req.rd_atomic, max_rd_atomic); }

if (mask & IB_QP_MAX_DEST_RD_ATOMIC) { - int max_dest_rd_atomic = - __roundup_pow_of_two(attr->max_dest_rd_atomic); + int max_dest_rd_atomic = attr->max_dest_rd_atomic ? + roundup_pow_of_two(attr->max_dest_rd_atomic) : 0;

qp->attr.max_dest_rd_atomic = max_dest_rd_atomic;

From: Amelie Delaunay amelie.delaunay@st.com

[ Upstream commit dfc708812a2acfc0ca56f56233b3c3e7b0d4ffe7 ]

To avoid race with vchan_complete, use the race free way to terminate running transfer.

Move vdesc->node list_del in stm32_mdma_start_transfer instead of in stm32_mdma_xfer_end to avoid another race in vchan_dma_desc_free_list.

Signed-off-by: Amelie Delaunay amelie.delaunay@st.com Link: https://lore.kernel.org/r/20200127085334.13163-7-amelie.delaunay@st.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/stm32-mdma.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/dma/stm32-mdma.c b/drivers/dma/stm32-mdma.c index 8c3c3e5b812a8..9c6867916e890 100644 --- a/drivers/dma/stm32-mdma.c +++ b/drivers/dma/stm32-mdma.c @@ -1137,6 +1137,8 @@ static void stm32_mdma_start_transfer(struct stm32_mdma_chan *chan) return; }

+ list_del(&vdesc->node); + chan->desc = to_stm32_mdma_desc(vdesc); hwdesc = chan->desc->node[0].hwdesc; chan->curr_hwdesc = 0; @@ -1252,8 +1254,10 @@ static int stm32_mdma_terminate_all(struct dma_chan *c) LIST_HEAD(head);

spin_lock_irqsave(&chan->vchan.lock, flags); - if (chan->busy) { - stm32_mdma_stop(chan); + if (chan->desc) { + vchan_terminate_vdesc(&chan->desc->vdesc); + if (chan->busy) + stm32_mdma_stop(chan); chan->desc = NULL; } vchan_get_all_descriptors(&chan->vchan, &head); @@ -1341,7 +1345,6 @@ static enum dma_status stm32_mdma_tx_status(struct dma_chan *c,

static void stm32_mdma_xfer_end(struct stm32_mdma_chan *chan) { - list_del(&chan->desc->vdesc.node); vchan_cookie_complete(&chan->desc->vdesc); chan->desc = NULL; chan->busy = false;

From: Dave Hansen dave.hansen@linux.intel.com

[ Upstream commit 16171bffc829272d5e6014bad48f680cb50943d9 ]

Alex Shi reported the pkey macros above arch_set_user_pkey_access() to be unused. They are unused, and even refer to a nonexistent CONFIG option.

But, they might have served a good use, which was to ensure that the code does not try to set values that would not fit in the PKRU register. As it stands, a too-large 'pkey' value would be likely to silently overflow the u32 new_pkru_bits.

Add a check to look for overflows. Also add a comment to remind any future developer to closely examine the types used to store pkey values if arch_max_pkey() ever changes.

This boots and passes the x86 pkey selftests.

Reported-by: Alex Shi alex.shi@linux.alibaba.com Signed-off-by: Dave Hansen dave.hansen@intel.com Signed-off-by: Borislav Petkov bp@suse.de Link: https://lkml.kernel.org/r/20200122165346.AD4DA150@viggo.jf.intel.com Signed-off-by: Sasha Levin sashal@kernel.org --- arch/x86/include/asm/pkeys.h | 5 +++++ arch/x86/kernel/fpu/xstate.c | 9 +++++++-- 2 files changed, 12 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h index 19b137f1b3beb..2ff9b98812b76 100644 --- a/arch/x86/include/asm/pkeys.h +++ b/arch/x86/include/asm/pkeys.h @@ -4,6 +4,11 @@

#define ARCH_DEFAULT_PKEY 0

+/* + * If more than 16 keys are ever supported, a thorough audit + * will be necessary to ensure that the types that store key + * numbers and masks have sufficient capacity. + */ #define arch_max_pkey() (boot_cpu_has(X86_FEATURE_OSPKE) ? 16 : 1)

extern int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c index 4b900035f2202..601a5da1d196a 100644 --- a/arch/x86/kernel/fpu/xstate.c +++ b/arch/x86/kernel/fpu/xstate.c @@ -907,8 +907,6 @@ const void *get_xsave_field_ptr(int xsave_state)

#ifdef CONFIG_ARCH_HAS_PKEYS

-#define NR_VALID_PKRU_BITS (CONFIG_NR_PROTECTION_KEYS * 2) -#define PKRU_VALID_MASK (NR_VALID_PKRU_BITS - 1) /* * This will go out and modify PKRU register to set the access * rights for @pkey to @init_val. @@ -927,6 +925,13 @@ int arch_set_user_pkey_access(struct task_struct *tsk, int pkey, if (!boot_cpu_has(X86_FEATURE_OSPKE)) return -EINVAL;

+ /* + * This code should only be called with valid 'pkey' + * values originating from in-kernel users. Complain + * if a bad value is observed. + */ + WARN_ON_ONCE(pkey >= arch_max_pkey()); + /* Set the bits we need in PKRU: */ if (init_val & PKEY_DISABLE_ACCESS) new_pkru_bits |= PKRU_AD_BIT;

From: Amelie Delaunay amelie.delaunay@st.com

[ Upstream commit d80cbef35bf89b763f06e03bb4ff8f933bf012c5 ]

To avoid race with vchan_complete, use the race free way to terminate running transfer.

Move vdesc->node list_del in stm32_dma_start_transfer instead of in stm32_mdma_chan_complete to avoid another race in vchan_dma_desc_free_list.

Signed-off-by: Amelie Delaunay amelie.delaunay@st.com Link: https://lore.kernel.org/r/20200129153628.29329-9-amelie.delaunay@st.com Signed-off-by: Vinod Koul vkoul@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/dma/stm32-dma.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

diff --git a/drivers/dma/stm32-dma.c b/drivers/dma/stm32-dma.c index 4903a408fc146..ac7af440f8658 100644 --- a/drivers/dma/stm32-dma.c +++ b/drivers/dma/stm32-dma.c @@ -494,8 +494,10 @@ static int stm32_dma_terminate_all(struct dma_chan *c)

spin_lock_irqsave(&chan->vchan.lock, flags);

- if (chan->busy) { - stm32_dma_stop(chan); + if (chan->desc) { + vchan_terminate_vdesc(&chan->desc->vdesc); + if (chan->busy) + stm32_dma_stop(chan); chan->desc = NULL; }

@@ -551,6 +553,8 @@ static void stm32_dma_start_transfer(struct stm32_dma_chan *chan) if (!vdesc) return;

+ list_del(&vdesc->node); + chan->desc = to_stm32_dma_desc(vdesc); chan->next_sg = 0; } @@ -628,7 +632,6 @@ static void stm32_dma_handle_chan_done(struct stm32_dma_chan *chan) } else { chan->busy = false; if (chan->next_sg == chan->desc->num_sgs) { - list_del(&chan->desc->vdesc.node); vchan_cookie_complete(&chan->desc->vdesc); chan->desc = NULL; }

From: Aric Cyr aric.cyr@amd.com

[ Upstream commit 6a6c4a4d459ecacc9013c45dcbf2bc9747fdbdbd ]

[Why] Since the i2c payload allocation can fail need to check return codes

[How] Clean up i2c payload allocations and check for errors

Signed-off-by: Aric Cyr aric.cyr@amd.com Reviewed-by: Joshua Aberback Joshua.Aberback@amd.com Acked-by: Rodrigo Siqueira Rodrigo.Siqueira@amd.com Acked-by: Harry Wentland harry.wentland@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../gpu/drm/amd/display/dc/core/dc_link_ddc.c | 52 +++++++++---------- 1 file changed, 25 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c index 46c9cb47a96e5..145af3bb2dfcb 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_ddc.c @@ -127,22 +127,16 @@ struct aux_payloads { struct vector payloads; };

-static struct i2c_payloads *dal_ddc_i2c_payloads_create(struct dc_context *ctx, uint32_t count) +static bool dal_ddc_i2c_payloads_create( + struct dc_context *ctx, + struct i2c_payloads *payloads, + uint32_t count) { - struct i2c_payloads *payloads; - - payloads = kzalloc(sizeof(struct i2c_payloads), GFP_KERNEL); - - if (!payloads) - return NULL; - if (dal_vector_construct( &payloads->payloads, ctx, count, sizeof(struct i2c_payload))) - return payloads; - - kfree(payloads); - return NULL; + return true;

+ return false; }

static struct i2c_payload *dal_ddc_i2c_payloads_get(struct i2c_payloads *p) @@ -155,14 +149,12 @@ static uint32_t dal_ddc_i2c_payloads_get_count(struct i2c_payloads *p) return p->payloads.count; }

-static void dal_ddc_i2c_payloads_destroy(struct i2c_payloads **p) +static void dal_ddc_i2c_payloads_destroy(struct i2c_payloads *p) { - if (!p || !*p) + if (!p) return; - dal_vector_destruct(&(*p)->payloads); - kfree(*p); - *p = NULL;

+ dal_vector_destruct(&p->payloads); }

static struct aux_payloads *dal_ddc_aux_payloads_create(struct dc_context *ctx, uint32_t count) @@ -580,9 +572,13 @@ bool dal_ddc_service_query_ddc_data(

uint32_t payloads_num = write_payloads + read_payloads;

+ if (write_size > EDID_SEGMENT_SIZE || read_size > EDID_SEGMENT_SIZE) return false;

+ if (!payloads_num) + return false; + /*TODO: len of payload data for i2c and aux is uint8!!!!, * but we want to read 256 over i2c!!!!*/ if (dal_ddc_service_is_in_aux_transaction_mode(ddc)) { @@ -613,23 +609,25 @@ bool dal_ddc_service_query_ddc_data( dal_ddc_aux_payloads_destroy(&payloads);

} else { - struct i2c_payloads *payloads = - dal_ddc_i2c_payloads_create(ddc->ctx, payloads_num); + struct i2c_command command = {0}; + struct i2c_payloads payloads;

- struct i2c_command command = { - .payloads = dal_ddc_i2c_payloads_get(payloads), - .number_of_payloads = 0, - .engine = DDC_I2C_COMMAND_ENGINE, - .speed = ddc->ctx->dc->caps.i2c_speed_in_khz }; + if (!dal_ddc_i2c_payloads_create(ddc->ctx, &payloads, payloads_num)) + return false; + + command.payloads = dal_ddc_i2c_payloads_get(&payloads); + command.number_of_payloads = 0; + command.engine = DDC_I2C_COMMAND_ENGINE; + command.speed = ddc->ctx->dc->caps.i2c_speed_in_khz;

dal_ddc_i2c_payloads_add( - payloads, address, write_size, write_buf, true); + &payloads, address, write_size, write_buf, true);

dal_ddc_i2c_payloads_add( - payloads, address, read_size, read_buf, false); + &payloads, address, read_size, read_buf, false);

command.number_of_payloads = - dal_ddc_i2c_payloads_get_count(payloads); + dal_ddc_i2c_payloads_get_count(&payloads);

ret = dm_helpers_submit_i2c( ddc->ctx,

From: Qian Cai cai@lca.pw

[ Upstream commit e00d996a4317aff5351c4338dd97d390225412c2 ]

Fields in "struct timer_rand_state" could be accessed concurrently. Lockless plain reads and writes result in data races. Fix them by adding pairs of READ|WRITE_ONCE(). The data races were reported by KCSAN,

BUG: KCSAN: data-race in add_timer_randomness / add_timer_randomness

write to 0xffff9f320a0a01d0 of 8 bytes by interrupt on cpu 22: add_timer_randomness+0x100/0x190 add_timer_randomness at drivers/char/random.c:1152 add_disk_randomness+0x85/0x280 scsi_end_request+0x43a/0x4a0 scsi_io_completion+0xb7/0x7e0 scsi_finish_command+0x1ed/0x2a0 scsi_softirq_done+0x1c9/0x1d0 blk_done_softirq+0x181/0x1d0 __do_softirq+0xd9/0x57c irq_exit+0xa2/0xc0 do_IRQ+0x8b/0x190 ret_from_intr+0x0/0x42 cpuidle_enter_state+0x15e/0x980 cpuidle_enter+0x69/0xc0 call_cpuidle+0x23/0x40 do_idle+0x248/0x280 cpu_startup_entry+0x1d/0x1f start_secondary+0x1b2/0x230 secondary_startup_64+0xb6/0xc0

no locks held by swapper/22/0. irq event stamp: 32871382 _raw_spin_unlock_irqrestore+0x53/0x60 _raw_spin_lock_irqsave+0x21/0x60 _local_bh_enable+0x21/0x30 irq_exit+0xa2/0xc0

read to 0xffff9f320a0a01d0 of 8 bytes by interrupt on cpu 2: add_timer_randomness+0xe8/0x190 add_disk_randomness+0x85/0x280 scsi_end_request+0x43a/0x4a0 scsi_io_completion+0xb7/0x7e0 scsi_finish_command+0x1ed/0x2a0 scsi_softirq_done+0x1c9/0x1d0 blk_done_softirq+0x181/0x1d0 __do_softirq+0xd9/0x57c irq_exit+0xa2/0xc0 do_IRQ+0x8b/0x190 ret_from_intr+0x0/0x42 cpuidle_enter_state+0x15e/0x980 cpuidle_enter+0x69/0xc0 call_cpuidle+0x23/0x40 do_idle+0x248/0x280 cpu_startup_entry+0x1d/0x1f start_secondary+0x1b2/0x230 secondary_startup_64+0xb6/0xc0

no locks held by swapper/2/0. irq event stamp: 37846304 _raw_spin_unlock_irqrestore+0x53/0x60 _raw_spin_lock_irqsave+0x21/0x60 _local_bh_enable+0x21/0x30 irq_exit+0xa2/0xc0

Reported by Kernel Concurrency Sanitizer on: Hardware name: HP ProLiant BL660c Gen9, BIOS I38 10/17/2018

Link: https://lore.kernel.org/r/1582648024-13111-1-git-send-email-cai@lca.pw Signed-off-by: Qian Cai cai@lca.pw Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/char/random.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/drivers/char/random.c b/drivers/char/random.c index 6a5d4dfafc474..80dedecfe15c5 100644 --- a/drivers/char/random.c +++ b/drivers/char/random.c @@ -1150,14 +1150,14 @@ static void add_timer_randomness(struct timer_rand_state *state, unsigned num) * We take into account the first, second and third-order deltas * in order to make our estimate. */ - delta = sample.jiffies - state->last_time; - state->last_time = sample.jiffies; + delta = sample.jiffies - READ_ONCE(state->last_time); + WRITE_ONCE(state->last_time, sample.jiffies);

- delta2 = delta - state->last_delta; - state->last_delta = delta; + delta2 = delta - READ_ONCE(state->last_delta); + WRITE_ONCE(state->last_delta, delta);

- delta3 = delta2 - state->last_delta2; - state->last_delta2 = delta2; + delta3 = delta2 - READ_ONCE(state->last_delta2); + WRITE_ONCE(state->last_delta2, delta2);

if (delta < 0) delta = -delta;

From: Takashi Iwai tiwai@suse.de

[ Upstream commit a3ea410cac41b19a5490aad7fe6d9a9a772e646e ]

Josef reported that his old-and-good Plextor ConvertX M402U video converter spews lots of WARNINGs on the recent kernels, and it turned out that the device uses a bulk endpoint for interrupt handling just like 2250 board.

For fixing it, generalize the check with the proper verification of the endpoint instead of hard-coded board type check.

Fixes: 7e5219d18e93 ("[media] go7007: Fix 2250 urb type") Reported-and-tested-by: Josef Möllers josef.moellers@suse.com BugLink: https://bugzilla.suse.com/show_bug.cgi?id=1162583 BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=206427

Signed-off-by: Takashi Iwai tiwai@suse.de 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 --- drivers/media/usb/go7007/go7007-usb.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/media/usb/go7007/go7007-usb.c b/drivers/media/usb/go7007/go7007-usb.c index 19c6a0354ce00..b84a6f6548610 100644 --- a/drivers/media/usb/go7007/go7007-usb.c +++ b/drivers/media/usb/go7007/go7007-usb.c @@ -1052,6 +1052,7 @@ static int go7007_usb_probe(struct usb_interface *intf, struct go7007_usb *usb; const struct go7007_usb_board *board; struct usb_device *usbdev = interface_to_usbdev(intf); + struct usb_host_endpoint *ep; unsigned num_i2c_devs; char *name; int video_pipe, i, v_urb_len; @@ -1148,7 +1149,8 @@ static int go7007_usb_probe(struct usb_interface *intf, if (usb->intr_urb->transfer_buffer == NULL) goto allocfail;

- if (go->board_id == GO7007_BOARDID_SENSORAY_2250) + ep = usb->usbdev->ep_in[4]; + if (usb_endpoint_type(&ep->desc) == USB_ENDPOINT_XFER_BULK) usb_fill_bulk_urb(usb->intr_urb, usb->usbdev, usb_rcvbulkpipe(usb->usbdev, 4), usb->intr_urb->transfer_buffer, 2*sizeof(u16),

From: Wen Yang wenyang@linux.alibaba.com

[ Upstream commit 4cbbc3a0eeed675449b1a4d080008927121f3da3 ]

While unlikely the divisor in scale64_check_overflow() could be >= 32bit in scale64_check_overflow(). do_div() truncates the divisor to 32bit at least on 32bit platforms.

Use div64_u64() instead to avoid the truncation to 32-bit.

[ tglx: Massaged changelog ]

Signed-off-by: Wen Yang wenyang@linux.alibaba.com Signed-off-by: Thomas Gleixner tglx@linutronix.de Link: https://lkml.kernel.org/r/20200120100523.45656-1-wenyang@linux.alibaba.com Signed-off-by: Sasha Levin sashal@kernel.org --- kernel/time/timekeeping.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c index 81ee5b83c9200..c66fd11d94bc4 100644 --- a/kernel/time/timekeeping.c +++ b/kernel/time/timekeeping.c @@ -1004,9 +1004,8 @@ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; - rem *= mult;

- do_div(rem, div); + rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; }

From: John Garry john.garry@huawei.com

[ Upstream commit 3f5777fbaf04c58d940526a22a2e0c813c837936 ]

The memory for global pointer is never freed during normal program execution, so let's do that in the main function exit as a good programming practice.

A stray blank line is also removed.

Reported-by: Jiri Olsa jolsa@redhat.com Signed-off-by: John Garry john.garry@huawei.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Andi Kleen ak@linux.intel.com Cc: James Clark james.clark@arm.com Cc: Joakim Zhang qiangqing.zhang@nxp.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Cc: Will Deacon will@kernel.org Cc: linuxarm@huawei.com Link: http://lore.kernel.org/lkml/1583406486-154841-2-git-send-email-john.garry@hu... Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/pmu-events/jevents.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c index c17e594041712..6631970f96832 100644 --- a/tools/perf/pmu-events/jevents.c +++ b/tools/perf/pmu-events/jevents.c @@ -1064,10 +1064,9 @@ static int process_one_file(const char *fpath, const struct stat *sb, */ int main(int argc, char *argv[]) { - int rc; + int rc, ret = 0; int maxfds; char ldirname[PATH_MAX]; - const char *arch; const char *output_file; const char *start_dirname; @@ -1138,7 +1137,8 @@ int main(int argc, char *argv[]) /* Make build fail */ fclose(eventsfp); free_arch_std_events(); - return 1; + ret = 1; + goto out_free_mapfile; } else if (rc) { goto empty_map; } @@ -1156,14 +1156,17 @@ int main(int argc, char *argv[]) /* Make build fail */ fclose(eventsfp); free_arch_std_events(); - return 1; + ret = 1; }

- return 0; + + goto out_free_mapfile;

empty_map: fclose(eventsfp); create_empty_mapping(output_file); free_arch_std_events(); - return 0; +out_free_mapfile: + free(mapfile); + return ret; }

From: John Clements john.clements@amd.com

[ Upstream commit 1b3460a8b19688ad3033b75237d40fa580a5a953 ]

mitigates race condition on BACO reset between GPU bootcode and driver reload

Reviewed-by: Hawking Zhang Hawking.Zhang@amd.com Signed-off-by: John Clements john.clements@amd.com Signed-off-by: Alex Deucher alexander.deucher@amd.com Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/gpu/drm/amd/amdgpu/atom.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/amd/amdgpu/atom.c b/drivers/gpu/drm/amd/amdgpu/atom.c index e9934de1b9cf8..0222bb7ea49b4 100644 --- a/drivers/gpu/drm/amd/amdgpu/atom.c +++ b/drivers/gpu/drm/amd/amdgpu/atom.c @@ -742,8 +742,8 @@ static void atom_op_jump(atom_exec_context *ctx, int *ptr, int arg) cjiffies = jiffies; if (time_after(cjiffies, ctx->last_jump_jiffies)) { cjiffies -= ctx->last_jump_jiffies; - if ((jiffies_to_msecs(cjiffies) > 5000)) { - DRM_ERROR("atombios stuck in loop for more than 5secs aborting\n"); + if ((jiffies_to_msecs(cjiffies) > 10000)) { + DRM_ERROR("atombios stuck in loop for more than 10secs aborting\n"); ctx->abort = true; } } else {

From: Wen Gong wgong@codeaurora.org

[ Upstream commit 402f2992b4d62760cce7c689ff216ea3bf4d6e8a ]

When use command to read values, it crashed.

command: dd if=/sys/kernel/debug/ieee80211/phy0/ath10k/mem_value count=1 bs=4 skip=$((0x100233))

It will call to ath10k_sdio_hif_diag_read with address = 0x4008cc and buf_len = 4.

Then system crash: [ 1786.013258] Unable to handle kernel paging request at virtual address ffffffc00bd45000 [ 1786.013273] Mem abort info: [ 1786.013281] ESR = 0x96000045 [ 1786.013291] Exception class = DABT (current EL), IL = 32 bits [ 1786.013299] SET = 0, FnV = 0 [ 1786.013307] EA = 0, S1PTW = 0 [ 1786.013314] Data abort info: [ 1786.013322] ISV = 0, ISS = 0x00000045 [ 1786.013330] CM = 0, WnR = 1 [ 1786.013342] swapper pgtable: 4k pages, 39-bit VAs, pgdp = 000000008542a60e [ 1786.013350] [ffffffc00bd45000] pgd=0000000000000000, pud=0000000000000000 [ 1786.013368] Internal error: Oops: 96000045 [#1] PREEMPT SMP [ 1786.013609] Process swapper/0 (pid: 0, stack limit = 0x0000000084b153c6) [ 1786.013623] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.19.86 #137 [ 1786.013631] Hardware name: MediaTek krane sku176 board (DT) [ 1786.013643] pstate: 80000085 (Nzcv daIf -PAN -UAO) [ 1786.013662] pc : __memcpy+0x94/0x180 [ 1786.013678] lr : swiotlb_tbl_unmap_single+0x84/0x150 [ 1786.013686] sp : ffffff8008003c60 [ 1786.013694] x29: ffffff8008003c90 x28: ffffffae96411f80 [ 1786.013708] x27: ffffffae960d2018 x26: ffffff8019a4b9a8 [ 1786.013721] x25: 0000000000000000 x24: 0000000000000001 [ 1786.013734] x23: ffffffae96567000 x22: 00000000000051d4 [ 1786.013747] x21: 0000000000000000 x20: 00000000fe6e9000 [ 1786.013760] x19: 0000000000000004 x18: 0000000000000020 [ 1786.013773] x17: 0000000000000001 x16: 0000000000000000 [ 1786.013787] x15: 00000000ffffffff x14: 00000000000044c0 [ 1786.013800] x13: 0000000000365ba4 x12: 0000000000000000 [ 1786.013813] x11: 0000000000000001 x10: 00000037be6e9000 [ 1786.013826] x9 : ffffffc940000000 x8 : 000000000bd45000 [ 1786.013839] x7 : 0000000000000000 x6 : ffffffc00bd45000 [ 1786.013852] x5 : 0000000000000000 x4 : 0000000000000000 [ 1786.013865] x3 : 0000000000000c00 x2 : 0000000000000004 [ 1786.013878] x1 : fffffff7be6e9004 x0 : ffffffc00bd45000 [ 1786.013891] Call trace: [ 1786.013903] __memcpy+0x94/0x180 [ 1786.013914] unmap_single+0x6c/0x84 [ 1786.013925] swiotlb_unmap_sg_attrs+0x54/0x80 [ 1786.013938] __swiotlb_unmap_sg_attrs+0x8c/0xa4 [ 1786.013952] msdc_unprepare_data+0x6c/0x84 [ 1786.013963] msdc_request_done+0x58/0x84 [ 1786.013974] msdc_data_xfer_done+0x1a0/0x1c8 [ 1786.013985] msdc_irq+0x12c/0x17c [ 1786.013996] __handle_irq_event_percpu+0xe4/0x250 [ 1786.014006] handle_irq_event_percpu+0x28/0x68 [ 1786.014015] handle_irq_event+0x48/0x78 [ 1786.014026] handle_fasteoi_irq+0xd0/0x1a0 [ 1786.014039] __handle_domain_irq+0x84/0xc4 [ 1786.014050] gic_handle_irq+0x124/0x1a4 [ 1786.014059] el1_irq+0xb0/0x128 [ 1786.014072] cpuidle_enter_state+0x298/0x328 [ 1786.014082] cpuidle_enter+0x30/0x40 [ 1786.014094] do_idle+0x190/0x268 [ 1786.014104] cpu_startup_entry+0x24/0x28 [ 1786.014116] rest_init+0xd4/0xe0 [ 1786.014126] start_kernel+0x30c/0x38c [ 1786.014139] Code: f8408423 f80084c3 36100062 b8404423 (b80044c3) [ 1786.014150] ---[ end trace 3b02ddb698ea69ee ]--- [ 1786.015415] Kernel panic - not syncing: Fatal exception in interrupt [ 1786.015433] SMP: stopping secondary CPUs [ 1786.015447] Kernel Offset: 0x2e8d200000 from 0xffffff8008000000 [ 1786.015458] CPU features: 0x0,2188200c [ 1786.015466] Memory Limit: none

For sdio chip, it need the memory which is kmalloc, if it is vmalloc from ath10k_mem_value_read, then it have a memory error. kzalloc of ath10k_sdio_hif_diag_read32 is the correct type, so add kzalloc in ath10k_sdio_hif_diag_read to replace the buffer which is vmalloc from ath10k_mem_value_read.

This patch only effect sdio chip.

Tested with QCA6174 SDIO with firmware WLAN.RMH.4.4.1-00029.

Signed-off-by: Wen Gong wgong@codeaurora.org Signed-off-by: Kalle Valo kvalo@codeaurora.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/wireless/ath/ath10k/sdio.c | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-)

diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c index 0ecaba824fb28..0cdaecb0e28a9 100644 --- a/drivers/net/wireless/ath/ath10k/sdio.c +++ b/drivers/net/wireless/ath/ath10k/sdio.c @@ -1567,23 +1567,33 @@ static int ath10k_sdio_hif_diag_read(struct ath10k *ar, u32 address, void *buf, size_t buf_len) { int ret; + void *mem; + + mem = kzalloc(buf_len, GFP_KERNEL); + if (!mem) + return -ENOMEM;

/* set window register to start read cycle */ ret = ath10k_sdio_write32(ar, MBOX_WINDOW_READ_ADDR_ADDRESS, address); if (ret) { ath10k_warn(ar, "failed to set mbox window read address: %d", ret); - return ret; + goto out; }

/* read the data */ - ret = ath10k_sdio_read(ar, MBOX_WINDOW_DATA_ADDRESS, buf, buf_len); + ret = ath10k_sdio_read(ar, MBOX_WINDOW_DATA_ADDRESS, mem, buf_len); if (ret) { ath10k_warn(ar, "failed to read from mbox window data address: %d\n", ret); - return ret; + goto out; }

- return 0; + memcpy(buf, mem, buf_len); + +out: + kfree(mem); + + return ret; }

static int ath10k_sdio_hif_diag_read32(struct ath10k *ar, u32 address,

From: Howard Chung howardchung@google.com

[ Upstream commit 96298f640104e4cd9a913a6e50b0b981829b94ff ]

According to Core Spec Version 5.2 | Vol 3, Part A 6.1.5, the incoming L2CAP_ConfigReq should be handled during OPEN state.

The section below shows the btmon trace when running L2CAP/COS/CFD/BV-12-C before and after this change.

=== Before === ...

ACL Data RX: Handle 256 flags 0x02 dlen 12 #22

L2CAP: Connection Request (0x02) ident 2 len 4 PSM: 1 (0x0001) Source CID: 65 < ACL Data TX: Handle 256 flags 0x00 dlen 16 #23 L2CAP: Connection Response (0x03) ident 2 len 8 Destination CID: 64 Source CID: 65 Result: Connection successful (0x0000) Status: No further information available (0x0000) < ACL Data TX: Handle 256 flags 0x00 dlen 12 #24 L2CAP: Configure Request (0x04) ident 2 len 4 Destination CID: 65 Flags: 0x0000

HCI Event: Number of Completed Packets (0x13) plen 5 #25

Num handles: 1 Handle: 256 Count: 1

HCI Event: Number of Completed Packets (0x13) plen 5 #26

Num handles: 1 Handle: 256 Count: 1

ACL Data RX: Handle 256 flags 0x02 dlen 16 #27

L2CAP: Configure Request (0x04) ident 3 len 8 Destination CID: 64 Flags: 0x0000 Option: Unknown (0x10) [hint] 01 00 .. < ACL Data TX: Handle 256 flags 0x00 dlen 18 #28 L2CAP: Configure Response (0x05) ident 3 len 10 Source CID: 65 Flags: 0x0000 Result: Success (0x0000) Option: Maximum Transmission Unit (0x01) [mandatory] MTU: 672

HCI Event: Number of Completed Packets (0x13) plen 5 #29

Num handles: 1 Handle: 256 Count: 1

ACL Data RX: Handle 256 flags 0x02 dlen 14 #30

L2CAP: Configure Response (0x05) ident 2 len 6 Source CID: 64 Flags: 0x0000 Result: Success (0x0000)

ACL Data RX: Handle 256 flags 0x02 dlen 20 #31

L2CAP: Configure Request (0x04) ident 3 len 12 Destination CID: 64 Flags: 0x0000 Option: Unknown (0x10) [hint] 01 00 91 02 11 11 ...... < ACL Data TX: Handle 256 flags 0x00 dlen 14 #32 L2CAP: Command Reject (0x01) ident 3 len 6 Reason: Invalid CID in request (0x0002) Destination CID: 64 Source CID: 65

HCI Event: Number of Completed Packets (0x13) plen 5 #33

Num handles: 1 Handle: 256 Count: 1 ... === After === ...

ACL Data RX: Handle 256 flags 0x02 dlen 12 #22

L2CAP: Connection Request (0x02) ident 2 len 4 PSM: 1 (0x0001) Source CID: 65 < ACL Data TX: Handle 256 flags 0x00 dlen 16 #23 L2CAP: Connection Response (0x03) ident 2 len 8 Destination CID: 64 Source CID: 65 Result: Connection successful (0x0000) Status: No further information available (0x0000) < ACL Data TX: Handle 256 flags 0x00 dlen 12 #24 L2CAP: Configure Request (0x04) ident 2 len 4 Destination CID: 65 Flags: 0x0000

HCI Event: Number of Completed Packets (0x13) plen 5 #25

Num handles: 1 Handle: 256 Count: 1

HCI Event: Number of Completed Packets (0x13) plen 5 #26

Num handles: 1 Handle: 256 Count: 1

ACL Data RX: Handle 256 flags 0x02 dlen 16 #27

L2CAP: Configure Request (0x04) ident 3 len 8 Destination CID: 64 Flags: 0x0000 Option: Unknown (0x10) [hint] 01 00 .. < ACL Data TX: Handle 256 flags 0x00 dlen 18 #28 L2CAP: Configure Response (0x05) ident 3 len 10 Source CID: 65 Flags: 0x0000 Result: Success (0x0000) Option: Maximum Transmission Unit (0x01) [mandatory] MTU: 672

HCI Event: Number of Completed Packets (0x13) plen 5 #29

Num handles: 1 Handle: 256 Count: 1

ACL Data RX: Handle 256 flags 0x02 dlen 14 #30

L2CAP: Configure Response (0x05) ident 2 len 6 Source CID: 64 Flags: 0x0000 Result: Success (0x0000)

ACL Data RX: Handle 256 flags 0x02 dlen 20 #31

L2CAP: Configure Request (0x04) ident 3 len 12 Destination CID: 64 Flags: 0x0000 Option: Unknown (0x10) [hint] 01 00 91 02 11 11 ..... < ACL Data TX: Handle 256 flags 0x00 dlen 18 #32 L2CAP: Configure Response (0x05) ident 3 len 10 Source CID: 65 Flags: 0x0000 Result: Success (0x0000) Option: Maximum Transmission Unit (0x01) [mandatory] MTU: 672 < ACL Data TX: Handle 256 flags 0x00 dlen 12 #33 L2CAP: Configure Request (0x04) ident 3 len 4 Destination CID: 65 Flags: 0x0000

HCI Event: Number of Completed Packets (0x13) plen 5 #34

Num handles: 1 Handle: 256 Count: 1

HCI Event: Number of Completed Packets (0x13) plen 5 #35

Num handles: 1 Handle: 256 Count: 1 ...

Signed-off-by: Howard Chung howardchung@google.com Signed-off-by: Marcel Holtmann marcel@holtmann.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/bluetooth/l2cap_core.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index b1f51cb007ea6..c04107d446016 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4117,7 +4117,8 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, return 0; }

- if (chan->state != BT_CONFIG && chan->state != BT_CONNECT2) { + if (chan->state != BT_CONFIG && chan->state != BT_CONNECT2 && + chan->state != BT_CONNECTED) { cmd_reject_invalid_cid(conn, cmd->ident, chan->scid, chan->dcid); goto unlock;

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

[ Upstream commit 1cb5deb5bc095c070c09a4540c45f9c9ba24be43 ]

If we decide that a directory free block is corrupt, we must take care not to leak a buffer pointer to the caller. After xfs_trans_brelse returns, the buffer can be freed or reused, which means that we have to set *bpp back to NULL.

Callers are supposed to notice the nonzero return value and not use the buffer pointer, but we should code more defensively, even if all current callers handle this situation correctly.

Fixes: de14c5f541e7 ("xfs: verify free block header fields") 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 --- fs/xfs/libxfs/xfs_dir2_node.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c index f1bb3434f51c7..01e99806b941f 100644 --- a/fs/xfs/libxfs/xfs_dir2_node.c +++ b/fs/xfs/libxfs/xfs_dir2_node.c @@ -214,6 +214,7 @@ __xfs_dir3_free_read( if (fa) { xfs_verifier_error(*bpp, -EFSCORRUPTED, fa); xfs_trans_brelse(tp, *bpp); + *bpp = NULL; return -EFSCORRUPTED; }

From: Dmitry Monakhov dmonakhov@gmail.com

[ Upstream commit eb5760863fc28feab28b567ddcda7e667e638da0 ]

We already has similar code in ext4_mb_complex_scan_group(), but ext4_mb_simple_scan_group() still affected.

Other reports: https://www.spinics.net/lists/linux-ext4/msg60231.html

Reviewed-by: Andreas Dilger adilger@dilger.ca Signed-off-by: Dmitry Monakhov dmonakhov@gmail.com Link: https://lore.kernel.org/r/20200310150156.641-1-dmonakhov@gmail.com Signed-off-by: Theodore Ts'o tytso@mit.edu Signed-off-by: Sasha Levin sashal@kernel.org --- fs/ext4/mballoc.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-)

diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 8dd54a8a03610..054cfdd007d69 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -1901,8 +1901,15 @@ void ext4_mb_simple_scan_group(struct ext4_allocation_context *ac, BUG_ON(buddy == NULL);

k = mb_find_next_zero_bit(buddy, max, 0); - BUG_ON(k >= max); - + if (k >= max) { + ext4_grp_locked_error(ac->ac_sb, e4b->bd_group, 0, 0, + "%d free clusters of order %d. But found 0", + grp->bb_counters[i], i); + ext4_mark_group_bitmap_corrupted(ac->ac_sb, + e4b->bd_group, + EXT4_GROUP_INFO_BBITMAP_CORRUPT); + break; + } ac->ac_found++;

ac->ac_b_ex.fe_len = 1 << i;

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 --- 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 304d905cb23fd..56f625371735f 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 --- 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 c24306af9758f..655079ae1dd1f 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 @@ retry: 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 --- 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 a790d5cf6ea37..684e8ae00d160 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 31cd0f327c8a2..e7fd60cf97804 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 3cf5863bc06e8..3c7ca2fa19597 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 --- 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 1fc9a7fa37b45..d29a58bd2f7a3 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 --- 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 4dc30e7890f6c..140386d7c75a3 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 --- 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 09f0dc3b967b1..60ca19eca1f63 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 --- 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 a7e555e413a69..cbd006fb7fbb9 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 --- 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 687c92ef76440..79942f7057576 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 --- 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 0d60f2f8f3eec..4b182ac15687e 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -255,11 +255,8 @@ 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 2e63c1106030b..e71075338ff5c 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 cc4273f119894..31c1496f938fb 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 --- 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 94dedabe648c2..6589ff51eaf5c 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 --- 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 c8ee8e801edb8..709c082dc9059 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 --- 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 a5df80d50d447..6cf3dd5edffda 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 9b91da09dc5f8..8d9812a51ef63 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 04c0ed41374f1..dd0528cf98183 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 137bf0cee897c..8fc9a4e911e3a 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 2517492dd1855..2fda9893962d1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1144,7 +1144,6 @@ 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 --- 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 28a3ad8b1d74b..137e1e8718d6f 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 --- 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 5dae7c85d9b6e..2c7d76b4c5e18 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 63d20308a9bb7..d419d89b91f7c 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 ad69430fd0eb5..5162fc1533c2f 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 --- mm/filemap.c | 8 ++++++++ 1 file changed, 8 insertions(+)

diff --git a/mm/filemap.c b/mm/filemap.c index 45f1c6d73b5b0..f2e777003b901 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2889,6 +2889,14 @@ filler: 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 --- 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 08f997a390d5d..cfd26437aeaea 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 @@ err_destroy_cq:

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 --- 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 751941a3ed303..aa451c8b49e56 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: Stephane Eranian eranian@google.com

[ Upstream commit bec49a9e05db3dbdca696fa07c62c52638fb6371 ]

When it is not possible for a non-privilege perf command to monitor at the kernel level (:k), the fallback code forces a :u. That works if the event was previously monitoring both levels. But if the event was already constrained to kernel only, then it does not make sense to restrict it to user only.

Given the code works by exclusion, a kernel only event would have:

attr->exclude_user = 1

The fallback code would add:

attr->exclude_kernel = 1

In the end the end would not monitor in either the user level or kernel level. In other words, it would count nothing.

An event programmed to monitor kernel only cannot be switched to user only without seriously warning the user.

This patch forces an error in this case to make it clear the request cannot really be satisfied.

Behavior with paranoid 1:

$ sudo bash -c "echo 1 > /proc/sys/kernel/perf_event_paranoid" $ perf stat -e cycles:k sleep 1

Performance counter stats for 'sleep 1':

1,520,413 cycles:k

1.002361664 seconds time elapsed

0.002480000 seconds user 0.000000000 seconds sys

Old behavior with paranoid 2:

$ sudo bash -c "echo 2 > /proc/sys/kernel/perf_event_paranoid" $ perf stat -e cycles:k sleep 1 Performance counter stats for 'sleep 1':

0 cycles:ku

1.002358127 seconds time elapsed

0.002384000 seconds user 0.000000000 seconds sys

New behavior with paranoid 2:

$ sudo bash -c "echo 2 > /proc/sys/kernel/perf_event_paranoid" $ perf stat -e cycles:k sleep 1 Error: You may not have permission to collect stats.

Consider tweaking /proc/sys/kernel/perf_event_paranoid, which controls use of the performance events system by unprivileged users (without CAP_PERFMON or CAP_SYS_ADMIN).

The current value is 2:

-1: Allow use of (almost) all events by all users Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK

= 0: Disallow ftrace function tracepoint by users without CAP_PERFMON or CAP_SYS_ADMIN

Disallow raw tracepoint access by users without CAP_SYS_PERFMON or CAP_SYS_ADMIN

= 1: Disallow CPU event access by users without CAP_PERFMON or CAP_SYS_ADMIN = 2: Disallow kernel profiling by users without CAP_PERFMON or CAP_SYS_ADMIN

To make this setting permanent, edit /etc/sysctl.conf too, e.g.:

kernel.perf_event_paranoid = -1

v2 of this patch addresses the review feedback from jolsa@redhat.com.

Signed-off-by: Stephane Eranian eranian@google.com Reviewed-by: Ian Rogers irogers@google.com Acked-by: Jiri Olsa jolsa@redhat.com Tested-by: Arnaldo Carvalho de Melo acme@redhat.com Cc: Alexander Shishkin alexander.shishkin@linux.intel.com Cc: Jiri Olsa jolsa@redhat.com Cc: Mark Rutland mark.rutland@arm.com Cc: Namhyung Kim namhyung@kernel.org Cc: Peter Zijlstra peterz@infradead.org Link: http://lore.kernel.org/lkml/20200414161550.225588-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo acme@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- tools/perf/util/evsel.c | 4 ++++ 1 file changed, 4 insertions(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c index 68c5ab0e1800b..e8586957562b3 100644 --- a/tools/perf/util/evsel.c +++ b/tools/perf/util/evsel.c @@ -2796,6 +2796,10 @@ bool perf_evsel__fallback(struct perf_evsel *evsel, int err, char *new_name; const char *sep = ":";

+ /* If event has exclude user then don't exclude kernel. */ + if (evsel->core.attr.exclude_user) + return false; + /* Is there already the separator in the name. */ if (strchr(name, '/') || strchr(name, ':'))