From: Luiz Augusto von Dentz luiz.von.dentz@intel.com

commit d0be8347c623e0ac4202a1d4e0373882821f56b0 upstream.

This fixes the following trace which is caused by hci_rx_work starting up *after* the final channel reference has been put() during sock_close() but *before* the references to the channel have been destroyed, so instead the code now rely on kref_get_unless_zero/l2cap_chan_hold_unless_zero to prevent referencing a channel that is about to be destroyed.

refcount_t: increment on 0; use-after-free. BUG: KASAN: use-after-free in refcount_dec_and_test+0x20/0xd0 Read of size 4 at addr ffffffc114f5bf18 by task kworker/u17:14/705

CPU: 4 PID: 705 Comm: kworker/u17:14 Tainted: G S W 4.14.234-00003-g1fb6d0bd49a4-dirty #28 Hardware name: Qualcomm Technologies, Inc. SM8150 V2 PM8150 Google Inc. MSM sm8150 Flame DVT (DT) Workqueue: hci0 hci_rx_work Call trace: dump_backtrace+0x0/0x378 show_stack+0x20/0x2c dump_stack+0x124/0x148 print_address_description+0x80/0x2e8 __kasan_report+0x168/0x188 kasan_report+0x10/0x18 __asan_load4+0x84/0x8c refcount_dec_and_test+0x20/0xd0 l2cap_chan_put+0x48/0x12c l2cap_recv_frame+0x4770/0x6550 l2cap_recv_acldata+0x44c/0x7a4 hci_acldata_packet+0x100/0x188 hci_rx_work+0x178/0x23c process_one_work+0x35c/0x95c worker_thread+0x4cc/0x960 kthread+0x1a8/0x1c4 ret_from_fork+0x10/0x18

Cc: stable@kernel.org Reported-by: Lee Jones lee.jones@linaro.org Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Tested-by: Lee Jones lee.jones@linaro.org Signed-off-by: Luiz Augusto von Dentz luiz.von.dentz@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/bluetooth/l2cap.h | 1 net/bluetooth/l2cap_core.c | 61 +++++++++++++++++++++++++++++++++--------- 2 files changed, 49 insertions(+), 13 deletions(-)

--- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -847,6 +847,7 @@ enum { };

void l2cap_chan_hold(struct l2cap_chan *c); +struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c); void l2cap_chan_put(struct l2cap_chan *c);

static inline void l2cap_chan_lock(struct l2cap_chan *chan) --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -111,7 +111,8 @@ static struct l2cap_chan *__l2cap_get_ch }

/* Find channel with given SCID. - * Returns locked channel. */ + * Returns a reference locked channel. + */ static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn, u16 cid) { @@ -119,15 +120,19 @@ static struct l2cap_chan *l2cap_get_chan

mutex_lock(&conn->chan_lock); c = __l2cap_get_chan_by_scid(conn, cid); - if (c) - l2cap_chan_lock(c); + if (c) { + /* Only lock if chan reference is not 0 */ + c = l2cap_chan_hold_unless_zero(c); + if (c) + l2cap_chan_lock(c); + } mutex_unlock(&conn->chan_lock);

return c; }

/* Find channel with given DCID. - * Returns locked channel. + * Returns a reference locked channel. */ static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn, u16 cid) @@ -136,8 +141,12 @@ static struct l2cap_chan *l2cap_get_chan

mutex_lock(&conn->chan_lock); c = __l2cap_get_chan_by_dcid(conn, cid); - if (c) - l2cap_chan_lock(c); + if (c) { + /* Only lock if chan reference is not 0 */ + c = l2cap_chan_hold_unless_zero(c); + if (c) + l2cap_chan_lock(c); + } mutex_unlock(&conn->chan_lock);

return c; @@ -162,8 +171,12 @@ static struct l2cap_chan *l2cap_get_chan

mutex_lock(&conn->chan_lock); c = __l2cap_get_chan_by_ident(conn, ident); - if (c) - l2cap_chan_lock(c); + if (c) { + /* Only lock if chan reference is not 0 */ + c = l2cap_chan_hold_unless_zero(c); + if (c) + l2cap_chan_lock(c); + } mutex_unlock(&conn->chan_lock);

return c; @@ -497,6 +510,16 @@ void l2cap_chan_hold(struct l2cap_chan * kref_get(&c->kref); }

+struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c) +{ + BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref)); + + if (!kref_get_unless_zero(&c->kref)) + return NULL; + + return c; +} + void l2cap_chan_put(struct l2cap_chan *c) { BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref)); @@ -1968,7 +1991,10 @@ static struct l2cap_chan *l2cap_global_c src_match = !bacmp(&c->src, src); dst_match = !bacmp(&c->dst, dst); if (src_match && dst_match) { - l2cap_chan_hold(c); + c = l2cap_chan_hold_unless_zero(c); + if (!c) + continue; + read_unlock(&chan_list_lock); return c; } @@ -1983,7 +2009,7 @@ static struct l2cap_chan *l2cap_global_c }

if (c1) - l2cap_chan_hold(c1); + c1 = l2cap_chan_hold_unless_zero(c1);

read_unlock(&chan_list_lock);

@@ -4463,6 +4489,7 @@ static inline int l2cap_config_req(struc

unlock: l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return err; }

@@ -4577,6 +4604,7 @@ static inline int l2cap_config_rsp(struc

done: l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return err; }

@@ -5304,6 +5332,7 @@ send_move_response: l2cap_send_move_chan_rsp(chan, result);

l2cap_chan_unlock(chan); + l2cap_chan_put(chan);

return 0; } @@ -5396,6 +5425,7 @@ static void l2cap_move_continue(struct l }

l2cap_chan_unlock(chan); + l2cap_chan_put(chan); }

static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid, @@ -5425,6 +5455,7 @@ static void l2cap_move_fail(struct l2cap l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED);

l2cap_chan_unlock(chan); + l2cap_chan_put(chan); }

static int l2cap_move_channel_rsp(struct l2cap_conn *conn, @@ -5488,6 +5519,7 @@ static int l2cap_move_channel_confirm(st l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid);

l2cap_chan_unlock(chan); + l2cap_chan_put(chan);

return 0; } @@ -5523,6 +5555,7 @@ static inline int l2cap_move_channel_con }

l2cap_chan_unlock(chan); + l2cap_chan_put(chan);

return 0; } @@ -5895,12 +5928,11 @@ static inline int l2cap_le_credits(struc if (credits > max_credits) { BT_ERR("LE credits overflow"); l2cap_send_disconn_req(chan, ECONNRESET); - l2cap_chan_unlock(chan);

/* Return 0 so that we don't trigger an unnecessary * command reject packet. */ - return 0; + goto unlock; }

chan->tx_credits += credits; @@ -5911,7 +5943,9 @@ static inline int l2cap_le_credits(struc if (chan->tx_credits) chan->ops->resume(chan);

+unlock: l2cap_chan_unlock(chan); + l2cap_chan_put(chan);

return 0; } @@ -7597,6 +7631,7 @@ drop:

done: l2cap_chan_unlock(chan); + l2cap_chan_put(chan); }

static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, @@ -8085,7 +8120,7 @@ static struct l2cap_chan *l2cap_global_f if (src_type != c->src_type) continue;

- l2cap_chan_hold(c); + c = l2cap_chan_hold_unless_zero(c); read_unlock(&chan_list_lock); return c; }

From: Linus Walleij linus.walleij@linaro.org

commit c5cdb9286913aa5a5ebb81bcca0c17df3b0e2c79 upstream.

Laurence reports:

"Kernel >5.18 on Zaurus has a bug where the power management code can't talk to devices, emitting the following errors:

sharpsl-pm sharpsl-pm: Error: AC check failed: voltage -22. sharpsl-pm sharpsl-pm: Charging Error! sharpsl-pm sharpsl-pm: Warning: Cannot read main battery!

Looking at the recent changes, I found that commit 31455bbda208 ("spi: pxa2xx_spi: Convert to use GPIO descriptors") replaced the deprecated SPI chip select platform device code with a gpiod lookup table. However, this didn't seem to work until I changed the `dev_id` member from the device name to the bus id. I'm not entirely sure why this is necessary, but I suspect it is related to the fact that in sysfs SPI devices are attached under /sys/devices/.../dev_name/spi_master/spiB/spiB.C, rather than directly to the device."

After reviewing the change I conclude that the same fix is needed for all affected boards.

Fixes: 31455bbda208 ("spi: pxa2xx_spi: Convert to use GPIO descriptors") Reported-by: Laurence de Bruxelles lfdebrux@gmail.com Signed-off-by: Linus Walleij linus.walleij@linaro.org Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220722114611.1517414-1-linus.walleij@linaro.org' Signed-off-by: Arnd Bergmann arnd@arndb.de Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/arm/mach-pxa/corgi.c | 2 +- arch/arm/mach-pxa/hx4700.c | 2 +- arch/arm/mach-pxa/icontrol.c | 4 ++-- arch/arm/mach-pxa/littleton.c | 2 +- arch/arm/mach-pxa/magician.c | 2 +- arch/arm/mach-pxa/spitz.c | 2 +- arch/arm/mach-pxa/z2.c | 4 ++-- 7 files changed, 9 insertions(+), 9 deletions(-)

--- a/arch/arm/mach-pxa/corgi.c +++ b/arch/arm/mach-pxa/corgi.c @@ -531,7 +531,7 @@ static struct pxa2xx_spi_controller corg };

static struct gpiod_lookup_table corgi_spi_gpio_table = { - .dev_id = "pxa2xx-spi.1", + .dev_id = "spi1", .table = { GPIO_LOOKUP_IDX("gpio-pxa", CORGI_GPIO_ADS7846_CS, "cs", 0, GPIO_ACTIVE_LOW), GPIO_LOOKUP_IDX("gpio-pxa", CORGI_GPIO_LCDCON_CS, "cs", 1, GPIO_ACTIVE_LOW), --- a/arch/arm/mach-pxa/hx4700.c +++ b/arch/arm/mach-pxa/hx4700.c @@ -635,7 +635,7 @@ static struct pxa2xx_spi_controller pxa_ };

static struct gpiod_lookup_table pxa_ssp2_gpio_table = { - .dev_id = "pxa2xx-spi.2", + .dev_id = "spi2", .table = { GPIO_LOOKUP_IDX("gpio-pxa", GPIO88_HX4700_TSC2046_CS, "cs", 0, GPIO_ACTIVE_LOW), { }, --- a/arch/arm/mach-pxa/icontrol.c +++ b/arch/arm/mach-pxa/icontrol.c @@ -140,7 +140,7 @@ struct platform_device pxa_spi_ssp4 = { };

static struct gpiod_lookup_table pxa_ssp3_gpio_table = { - .dev_id = "pxa2xx-spi.3", + .dev_id = "spi3", .table = { GPIO_LOOKUP_IDX("gpio-pxa", ICONTROL_MCP251x_nCS1, "cs", 0, GPIO_ACTIVE_LOW), GPIO_LOOKUP_IDX("gpio-pxa", ICONTROL_MCP251x_nCS2, "cs", 1, GPIO_ACTIVE_LOW), @@ -149,7 +149,7 @@ static struct gpiod_lookup_table pxa_ssp };

static struct gpiod_lookup_table pxa_ssp4_gpio_table = { - .dev_id = "pxa2xx-spi.4", + .dev_id = "spi4", .table = { GPIO_LOOKUP_IDX("gpio-pxa", ICONTROL_MCP251x_nCS3, "cs", 0, GPIO_ACTIVE_LOW), GPIO_LOOKUP_IDX("gpio-pxa", ICONTROL_MCP251x_nCS4, "cs", 1, GPIO_ACTIVE_LOW), --- a/arch/arm/mach-pxa/littleton.c +++ b/arch/arm/mach-pxa/littleton.c @@ -208,7 +208,7 @@ static struct spi_board_info littleton_s };

static struct gpiod_lookup_table littleton_spi_gpio_table = { - .dev_id = "pxa2xx-spi.2", + .dev_id = "spi2", .table = { GPIO_LOOKUP_IDX("gpio-pxa", LITTLETON_GPIO_LCD_CS, "cs", 0, GPIO_ACTIVE_LOW), { }, --- a/arch/arm/mach-pxa/magician.c +++ b/arch/arm/mach-pxa/magician.c @@ -946,7 +946,7 @@ static struct pxa2xx_spi_controller magi };

static struct gpiod_lookup_table magician_spi_gpio_table = { - .dev_id = "pxa2xx-spi.2", + .dev_id = "spi2", .table = { /* NOTICE must be GPIO, incompatibility with hw PXA SPI framing */ GPIO_LOOKUP_IDX("gpio-pxa", GPIO14_MAGICIAN_TSC2046_CS, "cs", 0, GPIO_ACTIVE_LOW), --- a/arch/arm/mach-pxa/spitz.c +++ b/arch/arm/mach-pxa/spitz.c @@ -578,7 +578,7 @@ static struct pxa2xx_spi_controller spit };

static struct gpiod_lookup_table spitz_spi_gpio_table = { - .dev_id = "pxa2xx-spi.2", + .dev_id = "spi2", .table = { GPIO_LOOKUP_IDX("gpio-pxa", SPITZ_GPIO_ADS7846_CS, "cs", 0, GPIO_ACTIVE_LOW), GPIO_LOOKUP_IDX("gpio-pxa", SPITZ_GPIO_LCDCON_CS, "cs", 1, GPIO_ACTIVE_LOW), --- a/arch/arm/mach-pxa/z2.c +++ b/arch/arm/mach-pxa/z2.c @@ -623,7 +623,7 @@ static struct pxa2xx_spi_controller pxa_ };

static struct gpiod_lookup_table pxa_ssp1_gpio_table = { - .dev_id = "pxa2xx-spi.1", + .dev_id = "spi1", .table = { GPIO_LOOKUP_IDX("gpio-pxa", GPIO24_ZIPITZ2_WIFI_CS, "cs", 0, GPIO_ACTIVE_LOW), { }, @@ -631,7 +631,7 @@ static struct gpiod_lookup_table pxa_ssp };

static struct gpiod_lookup_table pxa_ssp2_gpio_table = { - .dev_id = "pxa2xx-spi.2", + .dev_id = "spi2", .table = { GPIO_LOOKUP_IDX("gpio-pxa", GPIO88_ZIPITZ2_LCD_CS, "cs", 0, GPIO_ACTIVE_LOW), { },

From: Nadav Amit namit@vmware.com

commit d172b1a3bd065dd89234eac547fc62cf80681631 upstream.

Commit 824ddc601adc ("userfaultfd: provide unmasked address on page-fault") was introduced to fix an old bug, in which the offset in the address of a page-fault was masked. Concerns were raised - although were never backed by actual code - that some userspace code might break because the bug has been around for quite a while. To address these concerns a new flag was introduced, and only when this flag is set by the user, userfaultfd provides the exact address of the page-fault.

The commit however had a bug, and if the flag is unset, the offset was always masked based on a base-page granularity. Yet, for huge-pages, the behavior prior to the commit was that the address is masked to the huge-page granulrity.

While there are no reports on real breakage, fix this issue. If the flag is unset, use the address with the masking that was done before.

Link: https://lkml.kernel.org/r/20220711165906.2682-1-namit@vmware.com Fixes: 824ddc601adc ("userfaultfd: provide unmasked address on page-fault") Signed-off-by: Nadav Amit namit@vmware.com Reported-by: James Houghton jthoughton@google.com Reviewed-by: Mike Rapoport rppt@linux.ibm.com Reviewed-by: Peter Xu peterx@redhat.com Reviewed-by: James Houghton jthoughton@google.com Cc: David Hildenbrand david@redhat.com Cc: Jan Kara jack@suse.cz Cc: Andrea Arcangeli aarcange@redhat.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/userfaultfd.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-)

--- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -191,17 +191,19 @@ static inline void msg_init(struct uffd_ }

static inline struct uffd_msg userfault_msg(unsigned long address, + unsigned long real_address, unsigned int flags, unsigned long reason, unsigned int features) { struct uffd_msg msg; + msg_init(&msg); msg.event = UFFD_EVENT_PAGEFAULT;

- if (!(features & UFFD_FEATURE_EXACT_ADDRESS)) - address &= PAGE_MASK; - msg.arg.pagefault.address = address; + msg.arg.pagefault.address = (features & UFFD_FEATURE_EXACT_ADDRESS) ? + real_address : address; + /* * These flags indicate why the userfault occurred: * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault. @@ -485,8 +487,8 @@ vm_fault_t handle_userfault(struct vm_fa

init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function); uwq.wq.private = current; - uwq.msg = userfault_msg(vmf->real_address, vmf->flags, reason, - ctx->features); + uwq.msg = userfault_msg(vmf->address, vmf->real_address, vmf->flags, + reason, ctx->features); uwq.ctx = ctx; uwq.waken = false;

From: Andrei Vagin avagin@gmail.com

commit bdeb77bc2c405fa9f954c20269db175a0bd2793f upstream.

sendfile has to return EAGAIN if out_fd is nonblocking and the write into it would block.

Here is a small reproducer for the problem:

#define _GNU_SOURCE /* See feature_test_macros(7) */ #include <fcntl.h> #include <stdio.h> #include <unistd.h> #include <errno.h> #include <sys/stat.h> #include <sys/types.h> #include <sys/sendfile.h>

#define FILE_SIZE (1UL << 30) int main(int argc, char **argv) { int p[2], fd;

if (pipe2(p, O_NONBLOCK)) return 1;

fd = open(argv[1], O_RDWR | O_TMPFILE, 0666); if (fd < 0) return 1; ftruncate(fd, FILE_SIZE);

if (sendfile(p[1], fd, 0, FILE_SIZE) == -1) { fprintf(stderr, "FAIL\n"); } if (sendfile(p[1], fd, 0, FILE_SIZE) != -1 || errno != EAGAIN) { fprintf(stderr, "FAIL\n"); } return 0; }

It worked before b964bf53e540, it is stuck after b964bf53e540, and it works again with this fix.

This regression occurred because do_splice_direct() calls pipe_write that handles O_NONBLOCK. Here is a trace log from the reproducer:

1) | __x64_sys_sendfile64() { 1) | do_sendfile() { 1) | __fdget() 1) | rw_verify_area() 1) | __fdget() 1) | rw_verify_area() 1) | do_splice_direct() { 1) | rw_verify_area() 1) | splice_direct_to_actor() { 1) | do_splice_to() { 1) | rw_verify_area() 1) | generic_file_splice_read() 1) + 74.153 us | } 1) | direct_splice_actor() { 1) | iter_file_splice_write() { 1) | __kmalloc() 1) 0.148 us | pipe_lock(); 1) 0.153 us | splice_from_pipe_next.part.0(); 1) 0.162 us | page_cache_pipe_buf_confirm(); ... 16 times 1) 0.159 us | page_cache_pipe_buf_confirm(); 1) | vfs_iter_write() { 1) | do_iter_write() { 1) | rw_verify_area() 1) | do_iter_readv_writev() { 1) | pipe_write() { 1) | mutex_lock() 1) 0.153 us | mutex_unlock(); 1) 1.368 us | } 1) 1.686 us | } 1) 5.798 us | } 1) 6.084 us | } 1) 0.174 us | kfree(); 1) 0.152 us | pipe_unlock(); 1) + 14.461 us | } 1) + 14.783 us | } 1) 0.164 us | page_cache_pipe_buf_release(); ... 16 times 1) 0.161 us | page_cache_pipe_buf_release(); 1) | touch_atime() 1) + 95.854 us | } 1) + 99.784 us | } 1) ! 107.393 us | } 1) ! 107.699 us | }

Link: https://lkml.kernel.org/r/20220415005015.525191-1-avagin@gmail.com Fixes: b964bf53e540 ("teach sendfile(2) to handle send-to-pipe directly") Signed-off-by: Andrei Vagin avagin@gmail.com Cc: Al Viro viro@zeniv.linux.org.uk Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- fs/read_write.c | 3 +++ 1 file changed, 3 insertions(+)

--- a/fs/read_write.c +++ b/fs/read_write.c @@ -1247,6 +1247,9 @@ static ssize_t do_sendfile(int out_fd, i count, fl); file_end_write(out.file); } else { + if (out.file->f_flags & O_NONBLOCK) + fl |= SPLICE_F_NONBLOCK; + retval = splice_file_to_pipe(in.file, opipe, &pos, count, fl); }

From: Josef Bacik josef@toxicpanda.com

commit 3fe2895cfecd03ac74977f32102b966b6589f481 upstream.

We have an application with a lot of threads that use a shared mmap backed by tmpfs mounted with -o huge=within_size. This application started leaking loads of huge pages when we upgraded to a recent kernel.

Using the page ref tracepoints and a BPF program written by Tejun Heo we were able to determine that these pages would have multiple refcounts from the page fault path, but when it came to unmap time we wouldn't drop the number of refs we had added from the faults.

I wrote a reproducer that mmap'ed a file backed by tmpfs with -o huge=always, and then spawned 20 threads all looping faulting random offsets in this map, while using madvise(MADV_DONTNEED) randomly for huge page aligned ranges. This very quickly reproduced the problem.

The problem here is that we check for the case that we have multiple threads faulting in a range that was previously unmapped. One thread maps the PMD, the other thread loses the race and then returns 0. However at this point we already have the page, and we are no longer putting this page into the processes address space, and so we leak the page. We actually did the correct thing prior to f9ce0be71d1f, however it looks like Kirill copied what we do in the anonymous page case. In the anonymous page case we don't yet have a page, so we don't have to drop a reference on anything. Previously we did the correct thing for file based faults by returning VM_FAULT_NOPAGE so we correctly drop the reference on the page we faulted in.

Fix this by returning VM_FAULT_NOPAGE in the pmd_devmap_trans_unstable() case, this makes us drop the ref on the page properly, and now my reproducer no longer leaks the huge pages.

[josef@toxicpanda.com: v2] Link: https://lkml.kernel.org/r/e90c8f0dbae836632b669c2afc434006a00d4a67.165772147... Link: https://lkml.kernel.org/r/2b798acfd95c9ab9395fe85e8d5a835e2e10a920.165705113... Fixes: f9ce0be71d1f ("mm: Cleanup faultaround and finish_fault() codepaths") Signed-off-by: Josef Bacik josef@toxicpanda.com Signed-off-by: Rik van Riel riel@surriel.com Signed-off-by: Chris Mason clm@fb.com Acked-by: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Matthew Wilcox (Oracle) willy@infradead.org Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/memory.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

--- a/mm/memory.c +++ b/mm/memory.c @@ -4108,9 +4108,12 @@ vm_fault_t finish_fault(struct vm_fault return VM_FAULT_OOM; }

- /* See comment in handle_pte_fault() */ + /* + * See comment in handle_pte_fault() for how this scenario happens, we + * need to return NOPAGE so that we drop this page. + */ if (pmd_devmap_trans_unstable(vmf->pmd)) - return 0; + return VM_FAULT_NOPAGE;

vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd, vmf->address, &vmf->ptl);

From: Miaohe Lin linmiaohe@huawei.com

commit da9a298f5fad0dc615079a340da42928bc5b138e upstream.

When alloc_huge_page fails, *pagep is set to NULL without put_page first. So the hugepage indicated by *pagep is leaked.

Link: https://lkml.kernel.org/r/20220709092629.54291-1-linmiaohe@huawei.com Fixes: 8cc5fcbb5be8 ("mm, hugetlb: fix racy resv_huge_pages underflow on UFFDIO_COPY") Signed-off-by: Miaohe Lin linmiaohe@huawei.com Acked-by: Muchun Song songmuchun@bytedance.com Reviewed-by: Anshuman Khandual anshuman.khandual@arm.com Reviewed-by: Baolin Wang baolin.wang@linux.alibaba.com Reviewed-by: Mike Kravetz mike.kravetz@oracle.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/hugetlb.c | 1 + 1 file changed, 1 insertion(+)

--- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -5822,6 +5822,7 @@ int hugetlb_mcopy_atomic_pte(struct mm_s

page = alloc_huge_page(dst_vma, dst_addr, 0); if (IS_ERR(page)) { + put_page(*pagep); ret = -ENOMEM; *pagep = NULL; goto out;

From: Harald Freudenberger freude@linux.ibm.com

commit 918e75f77af7d2e049bb70469ec0a2c12782d96a upstream.

This patch slightly reworks the s390 arch_get_random_seed_{int,long} implementation: Make sure the CPACF trng instruction is never called in any interrupt context. This is done by adding an additional condition in_task().

Justification:

There are some constrains to satisfy for the invocation of the arch_get_random_seed_{int,long}() functions: - They should provide good random data during kernel initialization. - They should not be called in interrupt context as the TRNG instruction is relatively heavy weight and may for example make some network loads cause to timeout and buck.

However, it was not clear what kind of interrupt context is exactly encountered during kernel init or network traffic eventually calling arch_get_random_seed_long().

After some days of investigations it is clear that the s390 start_kernel function is not running in any interrupt context and so the trng is called:

Jul 11 18:33:39 t35lp54 kernel: [<00000001064e90ca>] arch_get_random_seed_long.part.0+0x32/0x70 Jul 11 18:33:39 t35lp54 kernel: [<000000010715f246>] random_init+0xf6/0x238 Jul 11 18:33:39 t35lp54 kernel: [<000000010712545c>] start_kernel+0x4a4/0x628 Jul 11 18:33:39 t35lp54 kernel: [<000000010590402a>] startup_continue+0x2a/0x40

The condition in_task() is true and the CPACF trng provides random data during kernel startup.

The network traffic however, is more difficult. A typical call stack looks like this:

Jul 06 17:37:07 t35lp54 kernel: [<000000008b5600fc>] extract_entropy.constprop.0+0x23c/0x240 Jul 06 17:37:07 t35lp54 kernel: [<000000008b560136>] crng_reseed+0x36/0xd8 Jul 06 17:37:07 t35lp54 kernel: [<000000008b5604b8>] crng_make_state+0x78/0x340 Jul 06 17:37:07 t35lp54 kernel: [<000000008b5607e0>] _get_random_bytes+0x60/0xf8 Jul 06 17:37:07 t35lp54 kernel: [<000000008b56108a>] get_random_u32+0xda/0x248 Jul 06 17:37:07 t35lp54 kernel: [<000000008aefe7a8>] kfence_guarded_alloc+0x48/0x4b8 Jul 06 17:37:07 t35lp54 kernel: [<000000008aeff35e>] __kfence_alloc+0x18e/0x1b8 Jul 06 17:37:07 t35lp54 kernel: [<000000008aef7f10>] __kmalloc_node_track_caller+0x368/0x4d8 Jul 06 17:37:07 t35lp54 kernel: [<000000008b611eac>] kmalloc_reserve+0x44/0xa0 Jul 06 17:37:07 t35lp54 kernel: [<000000008b611f98>] __alloc_skb+0x90/0x178 Jul 06 17:37:07 t35lp54 kernel: [<000000008b6120dc>] __napi_alloc_skb+0x5c/0x118 Jul 06 17:37:07 t35lp54 kernel: [<000000008b8f06b4>] qeth_extract_skb+0x13c/0x680 Jul 06 17:37:07 t35lp54 kernel: [<000000008b8f6526>] qeth_poll+0x256/0x3f8 Jul 06 17:37:07 t35lp54 kernel: [<000000008b63d76e>] __napi_poll.constprop.0+0x46/0x2f8 Jul 06 17:37:07 t35lp54 kernel: [<000000008b63dbec>] net_rx_action+0x1cc/0x408 Jul 06 17:37:07 t35lp54 kernel: [<000000008b937302>] __do_softirq+0x132/0x6b0 Jul 06 17:37:07 t35lp54 kernel: [<000000008abf46ce>] __irq_exit_rcu+0x13e/0x170 Jul 06 17:37:07 t35lp54 kernel: [<000000008abf531a>] irq_exit_rcu+0x22/0x50 Jul 06 17:37:07 t35lp54 kernel: [<000000008b922506>] do_io_irq+0xe6/0x198 Jul 06 17:37:07 t35lp54 kernel: [<000000008b935826>] io_int_handler+0xd6/0x110 Jul 06 17:37:07 t35lp54 kernel: [<000000008b9358a6>] psw_idle_exit+0x0/0xa Jul 06 17:37:07 t35lp54 kernel: ([<000000008ab9c59a>] arch_cpu_idle+0x52/0xe0) Jul 06 17:37:07 t35lp54 kernel: [<000000008b933cfe>] default_idle_call+0x6e/0xd0 Jul 06 17:37:07 t35lp54 kernel: [<000000008ac59f4e>] do_idle+0xf6/0x1b0 Jul 06 17:37:07 t35lp54 kernel: [<000000008ac5a28e>] cpu_startup_entry+0x36/0x40 Jul 06 17:37:07 t35lp54 kernel: [<000000008abb0d90>] smp_start_secondary+0x148/0x158 Jul 06 17:37:07 t35lp54 kernel: [<000000008b935b9e>] restart_int_handler+0x6e/0x90

which confirms that the call is in softirq context. So in_task() covers exactly the cases where we want to have CPACF trng called: not in nmi, not in hard irq, not in soft irq but in normal task context and during kernel init.

Signed-off-by: Harald Freudenberger freude@linux.ibm.com Acked-by: Jason A. Donenfeld Jason@zx2c4.com Reviewed-by: Juergen Christ jchrist@linux.ibm.com Link: https://lore.kernel.org/r/20220713131721.257907-1-freude@linux.ibm.com Fixes: e4f74400308c ("s390/archrandom: simplify back to earlier design and initialize earlier") [agordeev@linux.ibm.com changed desc, added Fixes and Link, removed -stable] Signed-off-by: Alexander Gordeev agordeev@linux.ibm.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- arch/s390/include/asm/archrandom.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)

--- a/arch/s390/include/asm/archrandom.h +++ b/arch/s390/include/asm/archrandom.h @@ -2,7 +2,7 @@ /* * Kernel interface for the s390 arch_random_* functions * - * Copyright IBM Corp. 2017, 2020 + * Copyright IBM Corp. 2017, 2022 * * Author: Harald Freudenberger freude@de.ibm.com * @@ -14,6 +14,7 @@ #ifdef CONFIG_ARCH_RANDOM

#include <linux/static_key.h> +#include <linux/preempt.h> #include <linux/atomic.h> #include <asm/cpacf.h>

@@ -32,7 +33,8 @@ static inline bool __must_check arch_get

static inline bool __must_check arch_get_random_seed_long(unsigned long *v) { - if (static_branch_likely(&s390_arch_random_available)) { + if (static_branch_likely(&s390_arch_random_available) && + in_task()) { cpacf_trng(NULL, 0, (u8 *)v, sizeof(*v)); atomic64_add(sizeof(*v), &s390_arch_random_counter); return true; @@ -42,7 +44,8 @@ static inline bool __must_check arch_get

static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { - if (static_branch_likely(&s390_arch_random_available)) { + if (static_branch_likely(&s390_arch_random_available) && + in_task()) { cpacf_trng(NULL, 0, (u8 *)v, sizeof(*v)); atomic64_add(sizeof(*v), &s390_arch_random_counter); return true;

From: Alistair Popple apopple@nvidia.com

commit 66cee9097e2b74ff3c8cc040ce5717c521a0c3fa upstream.

Users may request that pages from an OpenCL SVM allocation be migrated to the GPU with clEnqueueSVMMigrateMem(). In Nouveau this will call into nouveau_dmem_migrate_vma() to do the migration. If the total range to be migrated exceeds SG_MAX_SINGLE_ALLOC the pages will be migrated in chunks of size SG_MAX_SINGLE_ALLOC. However a typo in updating the starting address means that only the first chunk will get migrated.

Fix the calculation so that the entire range will get migrated if possible.

Signed-off-by: Alistair Popple apopple@nvidia.com Fixes: e3d8b0890469 ("drm/nouveau/svm: map pages after migration") Reviewed-by: Ralph Campbell rcampbell@nvidia.com Reviewed-by: Lyude Paul lyude@redhat.com Signed-off-by: Lyude Paul lyude@redhat.com Link: https://patchwork.freedesktop.org/patch/msgid/20220720062745.960701-1-apoppl... Cc: stable@vger.kernel.org # v5.8+ Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/gpu/drm/nouveau/nouveau_dmem.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -680,7 +680,11 @@ nouveau_dmem_migrate_vma(struct nouveau_ goto out_free_dma;

for (i = 0; i < npages; i += max) { - args.end = start + (max << PAGE_SHIFT); + if (args.start + (max << PAGE_SHIFT) > end) + args.end = end; + else + args.end = args.start + (max << PAGE_SHIFT); + ret = migrate_vma_setup(&args); if (ret) goto out_free_pfns;

From: David Howells dhowells@redhat.com

commit e0339f036ef4beb9b20f0b6532a1e0ece7f594c6 upstream.

Since __post_watch_notification() walks wlist->watchers with only the RCU read lock held, we need to use RCU methods to add to the list (we already use RCU methods to remove from the list).

Fix add_watch_to_object() to use hlist_add_head_rcu() instead of hlist_add_head() for that list.

Fixes: c73be61cede5 ("pipe: Add general notification queue support") Signed-off-by: David Howells dhowells@redhat.com Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/watch_queue.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/kernel/watch_queue.c +++ b/kernel/watch_queue.c @@ -494,7 +494,7 @@ int add_watch_to_object(struct watch *wa unlock_wqueue(wqueue); }

- hlist_add_head(&watch->list_node, &wlist->watchers); + hlist_add_head_rcu(&watch->list_node, &wlist->watchers); return 0; } EXPORT_SYMBOL(add_watch_to_object);

From: Kuniyuki Iwashima kuniyu@amazon.com

commit 58ebb1c8b35a8ef38cd6927431e0fa7b173a632d upstream.

While reading sysctl_tcp_dsack, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/tcp_input.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -4426,7 +4426,7 @@ static void tcp_dsack_set(struct sock *s { struct tcp_sock *tp = tcp_sk(sk);

- if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) { int mib_idx;

if (before(seq, tp->rcv_nxt)) @@ -4473,7 +4473,7 @@ static void tcp_send_dupack(struct sock NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);

- if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) { u32 end_seq = TCP_SKB_CB(skb)->end_seq;

tcp_rcv_spurious_retrans(sk, skb);

From: Kuniyuki Iwashima kuniyu@amazon.com

commit 36eeee75ef0157e42fb6593dcc65daab289b559e upstream.

While reading sysctl_tcp_adv_win_scale, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/tcp.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1437,7 +1437,7 @@ void tcp_select_initial_window(const str

static inline int tcp_win_from_space(const struct sock *sk, int space) { - int tcp_adv_win_scale = sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale; + int tcp_adv_win_scale = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_adv_win_scale);

return tcp_adv_win_scale <= 0 ? (space>>(-tcp_adv_win_scale)) :

From: Kuniyuki Iwashima kuniyu@amazon.com

commit 8499a2454d9e8a55ce616ede9f9580f36fd5b0f3 upstream.

While reading sysctl_tcp_nometrics_save, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/tcp_metrics.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -329,7 +329,7 @@ void tcp_update_metrics(struct sock *sk) int m;

sk_dst_confirm(sk); - if (net->ipv4.sysctl_tcp_nometrics_save || !dst) + if (READ_ONCE(net->ipv4.sysctl_tcp_nometrics_save) || !dst) return;

rcu_read_lock();

From: Benjamin Poirier bpoirier@nvidia.com

commit 9b134b1694ec8926926ba6b7b80884ea829245a0 upstream.

After commit b6c02ef54913 ("bridge: Netlink interface fix."), br_fill_ifinfo() started to send an empty IFLA_AF_SPEC attribute when a bridge vlan dump is requested but an interface does not have any vlans configured.

iproute2 ignores such an empty attribute since commit b262a9becbcb ("bridge: Fix output with empty vlan lists") but older iproute2 versions as well as other utilities have their output changed by the cited kernel commit, resulting in failed test cases. Regardless, emitting an empty attribute is pointless and inefficient.

Avoid this change by canceling the attribute if no AF_SPEC data was added.

Fixes: b6c02ef54913 ("bridge: Netlink interface fix.") Reviewed-by: Ido Schimmel idosch@nvidia.com Signed-off-by: Benjamin Poirier bpoirier@nvidia.com Acked-by: Nikolay Aleksandrov razor@blackwall.org Link: https://lore.kernel.org/r/20220725001236.95062-1-bpoirier@nvidia.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_netlink.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-)

--- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -589,9 +589,13 @@ static int br_fill_ifinfo(struct sk_buff }

done: + if (af) { + if (nlmsg_get_pos(skb) - (void *)af > nla_attr_size(0)) + nla_nest_end(skb, af); + else + nla_nest_cancel(skb, af); + }

- if (af) - nla_nest_end(skb, af); nlmsg_end(skb, nlh); return 0;

From: Maciej Fijalkowski maciej.fijalkowski@intel.com

commit 283d736ff7c7e96ac5b32c6c0de40372f8eb171e upstream.

Tx side sets EOP and RS bits on descriptors to indicate that a particular descriptor is the last one and needs to generate an irq when it was sent. These bits should not be checked on completion path regardless whether it's the Tx or the Rx. DD bit serves this purpose and it indicates that a particular descriptor is either for Rx or was successfully Txed. EOF is also set as loopback test does not xmit fragmented frames.

Look at (DD | EOF) bits setting in ice_lbtest_receive_frames() instead of EOP and RS pair.

Fixes: 0e674aeb0b77 ("ice: Add handler for ethtool selftest") Signed-off-by: Maciej Fijalkowski maciej.fijalkowski@intel.com Tested-by: George Kuruvinakunnel george.kuruvinakunnel@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/intel/ice/ice_ethtool.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

--- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -660,7 +660,8 @@ static int ice_lbtest_receive_frames(str rx_desc = ICE_RX_DESC(rx_ring, i);

if (!(rx_desc->wb.status_error0 & - cpu_to_le16(ICE_TX_DESC_CMD_EOP | ICE_TX_DESC_CMD_RS))) + (cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_DD_S)) | + cpu_to_le16(BIT(ICE_RX_FLEX_DESC_STATUS0_EOF_S))))) continue;

rx_buf = &rx_ring->rx_buf[i];

From: Anirudh Venkataramanan anirudh.venkataramanan@intel.com

commit 5c8e3c7ff3e7bd7b938659be704f75cc746b697f upstream.

The driver currently does not allow two VSIs in the same PF domain to have the same unicast MAC address. This is incorrect in the sense that a policy decision is being made in the driver when it must be left to the user. This approach was causing issues when rebooting the system with VFs spawned not being able to change their MAC addresses. Such errors were present in dmesg:

[ 7921.068237] ice 0000:b6:00.2 ens2f2: Unicast MAC 6a:0d:e4:70:ca:d1 already exists on this PF. Preventing setting VF 7 unicast MAC address to 6a:0d:e4:70:ca:d1

Fix that by removing this restriction. Doing this also allows us to remove some additional code that's checking if a unicast MAC filter already exists.

Fixes: 47ebc7b02485 ("ice: Check if unicast MAC exists before setting VF MAC") Signed-off-by: Anirudh Venkataramanan anirudh.venkataramanan@intel.com Signed-off-by: Sylwester Dziedziuch sylwesterx.dziedziuch@intel.com Signed-off-by: Mateusz Palczewski mateusz.palczewski@intel.com Signed-off-by: Jedrzej Jagielski jedrzej.jagielski@intel.com Tested-by: Marek Szlosek marek.szlosek@intel.com Signed-off-by: Tony Nguyen anthony.l.nguyen@intel.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/net/ethernet/intel/ice/ice_main.c | 2 + drivers/net/ethernet/intel/ice/ice_sriov.c | 40 ----------------------------- 2 files changed, 2 insertions(+), 40 deletions(-)

--- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4640,6 +4640,8 @@ ice_probe(struct pci_dev *pdev, const st ice_set_safe_mode_caps(hw); }

+ hw->ucast_shared = true; + err = ice_init_pf(pf); if (err) { dev_err(dev, "ice_init_pf failed: %d\n", err); --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -1310,39 +1310,6 @@ out_put_vf: }

/** - * ice_unicast_mac_exists - check if the unicast MAC exists on the PF's switch - * @pf: PF used to reference the switch's rules - * @umac: unicast MAC to compare against existing switch rules - * - * Return true on the first/any match, else return false - */ -static bool ice_unicast_mac_exists(struct ice_pf *pf, u8 *umac) -{ - struct ice_sw_recipe *mac_recipe_list = - &pf->hw.switch_info->recp_list[ICE_SW_LKUP_MAC]; - struct ice_fltr_mgmt_list_entry *list_itr; - struct list_head *rule_head; - struct mutex *rule_lock; /* protect MAC filter list access */ - - rule_head = &mac_recipe_list->filt_rules; - rule_lock = &mac_recipe_list->filt_rule_lock; - - mutex_lock(rule_lock); - list_for_each_entry(list_itr, rule_head, list_entry) { - u8 *existing_mac = &list_itr->fltr_info.l_data.mac.mac_addr[0]; - - if (ether_addr_equal(existing_mac, umac)) { - mutex_unlock(rule_lock); - return true; - } - } - - mutex_unlock(rule_lock); - - return false; -} - -/** * ice_set_vf_mac * @netdev: network interface device structure * @vf_id: VF identifier @@ -1376,13 +1343,6 @@ int ice_set_vf_mac(struct net_device *ne if (ret) goto out_put_vf;

- if (ice_unicast_mac_exists(pf, mac)) { - netdev_err(netdev, "Unicast MAC %pM already exists on this PF. Preventing setting VF %u unicast MAC address to %pM\n", - mac, vf_id, mac); - ret = -EINVAL; - goto out_put_vf; - } - mutex_lock(&vf->cfg_lock);

/* VF is notified of its new MAC via the PF's response to the

From: Wei Wang weiwan@google.com

commit 4d8f24eeedc58d5f87b650ddda73c16e8ba56559 upstream.

This reverts commit 4a41f453bedfd5e9cd040bad509d9da49feb3e2c.

This to-be-reverted commit was meant to apply a stricter rule for the stack to enter pingpong mode. However, the condition used to check for interactive session "before(tp->lsndtime, icsk->icsk_ack.lrcvtime)" is jiffy based and might be too coarse, which delays the stack entering pingpong mode. We revert this patch so that we no longer use the above condition to determine interactive session, and also reduce pingpong threshold to 1.

Fixes: 4a41f453bedf ("tcp: change pingpong threshold to 3") Reported-by: LemmyHuang hlm3280@163.com Suggested-by: Neal Cardwell ncardwell@google.com Signed-off-by: Wei Wang weiwan@google.com Acked-by: Neal Cardwell ncardwell@google.com Reviewed-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20220721204404.388396-1-weiwan@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/inet_connection_sock.h | 10 +--------- net/ipv4/tcp_output.c | 15 ++++++--------- 2 files changed, 7 insertions(+), 18 deletions(-)

--- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -323,7 +323,7 @@ void inet_csk_update_fastreuse(struct in

struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);

-#define TCP_PINGPONG_THRESH 3 +#define TCP_PINGPONG_THRESH 1

static inline void inet_csk_enter_pingpong_mode(struct sock *sk) { @@ -340,14 +340,6 @@ static inline bool inet_csk_in_pingpong_ return inet_csk(sk)->icsk_ack.pingpong >= TCP_PINGPONG_THRESH; }

-static inline void inet_csk_inc_pingpong_cnt(struct sock *sk) -{ - struct inet_connection_sock *icsk = inet_csk(sk); - - if (icsk->icsk_ack.pingpong < U8_MAX) - icsk->icsk_ack.pingpong++; -} - static inline bool inet_csk_has_ulp(struct sock *sk) { return inet_sk(sk)->is_icsk && !!inet_csk(sk)->icsk_ulp_ops; --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -167,16 +167,13 @@ static void tcp_event_data_sent(struct t if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START);

- /* If this is the first data packet sent in response to the - * previous received data, - * and it is a reply for ato after last received packet, - * increase pingpong count. - */ - if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) && - (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) - inet_csk_inc_pingpong_cnt(sk); - tp->lsndtime = now; + + /* If it is a reply for ato after last received + * packet, enter pingpong mode. + */ + if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) + inet_csk_enter_pingpong_mode(sk); }

/* Account for an ACK we sent. */

From: Eric Dumazet edumazet@google.com

commit e62d2e110356093c034998e093675df83057e511 upstream.

After the blamed commit, IPv4 SYN packets handled by a dual stack IPv6 socket are dropped, even if perfectly valid.

$ nstat | grep MD5 TcpExtTCPMD5Failure 5 0.0

For a dual stack listener, an incoming IPv4 SYN packet would call tcp_inbound_md5_hash() with @family == AF_INET, while tp->af_specific is pointing to tcp_sock_ipv6_specific.

Only later when an IPv4-mapped child is created, tp->af_specific is changed to tcp_sock_ipv6_mapped_specific.

Fixes: 7bbb765b7349 ("net/tcp: Merge TCP-MD5 inbound callbacks") Reported-by: Brian Vazquez brianvv@google.com Signed-off-by: Eric Dumazet edumazet@google.com Reviewed-by: David Ahern dsahern@kernel.org Reviewed-by: Dmitry Safonov dima@arista.com Tested-by: Leonard Crestez cdleonard@gmail.com Link: https://lore.kernel.org/r/20220726115743.2759832-1-edumazet@google.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/tcp.c | 15 ++++++++++++--- 1 file changed, 12 insertions(+), 3 deletions(-)

--- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -4481,9 +4481,18 @@ tcp_inbound_md5_hash(const struct sock * return SKB_DROP_REASON_TCP_MD5UNEXPECTED; }

- /* check the signature */ - genhash = tp->af_specific->calc_md5_hash(newhash, hash_expected, - NULL, skb); + /* Check the signature. + * To support dual stack listeners, we need to handle + * IPv4-mapped case. + */ + if (family == AF_INET) + genhash = tcp_v4_md5_hash_skb(newhash, + hash_expected, + NULL, skb); + else + genhash = tp->af_specific->calc_md5_hash(newhash, + hash_expected, + NULL, skb);

if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);

From: Kuniyuki Iwashima kuniyu@amazon.com

commit 9fb90193fbd66b4c5409ef729fd081861f8b6351 upstream.

While reading sysctl_tcp_limit_output_bytes, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader.

Fixes: 46d3ceabd8d9 ("tcp: TCP Small Queues") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/tcp_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2502,7 +2502,7 @@ static bool tcp_small_queue_check(struct sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, - sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes); + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes)); limit <<= factor;

if (static_branch_unlikely(&tcp_tx_delay_enabled) &&

From: Jason Yan yanaijie@huawei.com

commit d9a434fa0c12ed5f7afe1e9dd30003ab5d059b85 upstream.

As explained in SG_IO howto[1]:

"If iovec_count is non-zero then 'dxfer_len' should be equal to the sum of iov_len lengths. If not, the minimum of the two is the transfer length."

When iovec_count is non-zero and dxfer_len is zero, the sg_io() just genarated a null bio, and finally caused a warning below. To fix it, skip generating a bio for this request if dxfer_len is zero.

[1] https://tldp.org/HOWTO/SCSI-Generic-HOWTO/x198.html

WARNING: CPU: 2 PID: 3643 at drivers/scsi/scsi_lib.c:1032 scsi_alloc_sgtables+0xc7d/0xf70 drivers/scsi/scsi_lib.c:1032 Modules linked in:

CPU: 2 PID: 3643 Comm: syz-executor397 Not tainted 5.17.0-rc3-syzkaller-00316-gb81b1829e7e3 #0 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.14.0-204/01/2014 RIP: 0010:scsi_alloc_sgtables+0xc7d/0xf70 drivers/scsi/scsi_lib.c:1032 Code: e7 fc 31 ff 44 89 f6 e8 c1 4e e7 fc 45 85 f6 0f 84 1a f5 ff ff e8 93 4c e7 fc 83 c5 01 0f b7 ed e9 0f f5 ff ff e8 83 4c e7 fc <0f> 0b 41 bc 0a 00 00 00 e9 2b fb ff ff 41 bc 09 00 00 00 e9 20 fb RSP: 0018:ffffc90000d07558 EFLAGS: 00010293 RAX: 0000000000000000 RBX: ffff88801bfc96a0 RCX: 0000000000000000 RDX: ffff88801c876000 RSI: ffffffff849060bd RDI: 0000000000000003 RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff849055b9 R11: 0000000000000000 R12: ffff888012b8c000 R13: ffff88801bfc9580 R14: 0000000000000000 R15: ffff88801432c000 FS: 00007effdec8e700(0000) GS:ffff88802cc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007effdec6d718 CR3: 00000000206d6000 CR4: 0000000000150ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> scsi_setup_scsi_cmnd drivers/scsi/scsi_lib.c:1219 [inline] scsi_prepare_cmd drivers/scsi/scsi_lib.c:1614 [inline] scsi_queue_rq+0x283e/0x3630 drivers/scsi/scsi_lib.c:1730 blk_mq_dispatch_rq_list+0x6ea/0x22e0 block/blk-mq.c:1851 __blk_mq_sched_dispatch_requests+0x20b/0x410 block/blk-mq-sched.c:299 blk_mq_sched_dispatch_requests+0xfb/0x180 block/blk-mq-sched.c:332 __blk_mq_run_hw_queue+0xf9/0x350 block/blk-mq.c:1968 __blk_mq_delay_run_hw_queue+0x5b6/0x6c0 block/blk-mq.c:2045 blk_mq_run_hw_queue+0x30f/0x480 block/blk-mq.c:2096 blk_mq_sched_insert_request+0x340/0x440 block/blk-mq-sched.c:451 blk_execute_rq+0xcc/0x340 block/blk-mq.c:1231 sg_io+0x67c/0x1210 drivers/scsi/scsi_ioctl.c:485 scsi_ioctl_sg_io drivers/scsi/scsi_ioctl.c:866 [inline] scsi_ioctl+0xa66/0x1560 drivers/scsi/scsi_ioctl.c:921 sd_ioctl+0x199/0x2a0 drivers/scsi/sd.c:1576 blkdev_ioctl+0x37a/0x800 block/ioctl.c:588 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:874 [inline] __se_sys_ioctl fs/ioctl.c:860 [inline] __x64_sys_ioctl+0x193/0x200 fs/ioctl.c:860 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae RIP: 0033:0x7effdecdc5d9 Code: 28 00 00 00 75 05 48 83 c4 28 c3 e8 81 14 00 00 90 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 b8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007effdec8e2f8 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00007effded664c0 RCX: 00007effdecdc5d9 RDX: 0000000020002300 RSI: 0000000000002285 RDI: 0000000000000004 RBP: 00007effded34034 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000003 R13: 00007effded34054 R14: 2f30656c69662f2e R15: 00007effded664c8

Link: https://lore.kernel.org/r/20220720025120.3226770-1-yanaijie@huawei.com Fixes: 25636e282fe9 ("block: fix SG_IO vector request data length handling") Reported-by: syzbot+d44b35ecfb807e5af0b5@syzkaller.appspotmail.com Reviewed-by: Christoph Hellwig hch@lst.de Reviewed-by: Bart Van Assche bvanassche@acm.org Signed-off-by: Jason Yan yanaijie@huawei.com Signed-off-by: Martin K. Petersen martin.petersen@oracle.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/scsi/scsi_ioctl.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/drivers/scsi/scsi_ioctl.c +++ b/drivers/scsi/scsi_ioctl.c @@ -450,7 +450,7 @@ static int sg_io(struct scsi_device *sde goto out_put_request;

ret = 0; - if (hdr->iovec_count) { + if (hdr->iovec_count && hdr->dxfer_len) { struct iov_iter i; struct iovec *iov = NULL;

From: Kuniyuki Iwashima kuniyu@amazon.com

commit e27326009a3d247b831eda38878c777f6f4eb3d1 upstream.

When we close ping6 sockets, some resources are left unfreed because pingv6_prot is missing sk->sk_prot->destroy(). As reported by syzbot [0], just three syscalls leak 96 bytes and easily cause OOM.

struct ipv6_sr_hdr *hdr; char data[24] = {0}; int fd;

hdr = (struct ipv6_sr_hdr *)data; hdr->hdrlen = 2; hdr->type = IPV6_SRCRT_TYPE_4;

fd = socket(AF_INET6, SOCK_DGRAM, NEXTHDR_ICMP); setsockopt(fd, IPPROTO_IPV6, IPV6_RTHDR, data, 24); close(fd);

To fix memory leaks, let's add a destroy function.

Note the socket() syscall checks if the GID is within the range of net.ipv4.ping_group_range. The default value is [1, 0] so that no GID meets the condition (1 <= GID <= 0). Thus, the local DoS does not succeed until we change the default value. However, at least Ubuntu/Fedora/RHEL loosen it.

$ cat /usr/lib/sysctl.d/50-default.conf ... -net.ipv4.ping_group_range = 0 2147483647

Also, there could be another path reported with these options, and some of them require CAP_NET_RAW.

setsockopt IPV6_ADDRFORM (inet6_sk(sk)->pktoptions) IPV6_RECVPATHMTU (inet6_sk(sk)->rxpmtu) IPV6_HOPOPTS (inet6_sk(sk)->opt) IPV6_RTHDRDSTOPTS (inet6_sk(sk)->opt) IPV6_RTHDR (inet6_sk(sk)->opt) IPV6_DSTOPTS (inet6_sk(sk)->opt) IPV6_2292PKTOPTIONS (inet6_sk(sk)->opt)

getsockopt IPV6_FLOWLABEL_MGR (inet6_sk(sk)->ipv6_fl_list)

For the record, I left a different splat with syzbot's one.

unreferenced object 0xffff888006270c60 (size 96): comm "repro2", pid 231, jiffies 4294696626 (age 13.118s) hex dump (first 32 bytes): 01 00 00 00 44 00 00 00 00 00 00 00 00 00 00 00 ....D........... 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000f6bc7ea9>] sock_kmalloc (net/core/sock.c:2564 net/core/sock.c:2554) [<000000006d699550>] do_ipv6_setsockopt.constprop.0 (net/ipv6/ipv6_sockglue.c:715) [<00000000c3c3b1f5>] ipv6_setsockopt (net/ipv6/ipv6_sockglue.c:1024) [<000000007096a025>] __sys_setsockopt (net/socket.c:2254) [<000000003a8ff47b>] __x64_sys_setsockopt (net/socket.c:2265 net/socket.c:2262 net/socket.c:2262) [<000000007c409dcb>] do_syscall_64 (arch/x86/entry/common.c:50 arch/x86/entry/common.c:80) [<00000000e939c4a9>] entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:120)

[0]: https://syzkaller.appspot.com/bug?extid=a8430774139ec3ab7176

Fixes: 6d0bfe226116 ("net: ipv6: Add IPv6 support to the ping socket.") Reported-by: syzbot+a8430774139ec3ab7176@syzkaller.appspotmail.com Reported-by: Ayushman Dutta ayudutta@amazon.com Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Reviewed-by: David Ahern dsahern@kernel.org Reviewed-by: Eric Dumazet edumazet@google.com Link: https://lore.kernel.org/r/20220728012220.46918-1-kuniyu@amazon.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/ping.c | 6 ++++++ 1 file changed, 6 insertions(+)

--- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -22,6 +22,11 @@ #include <linux/proc_fs.h> #include <net/ping.h>

+static void ping_v6_destroy(struct sock *sk) +{ + inet6_destroy_sock(sk); +} + /* Compatibility glue so we can support IPv6 when it's compiled as a module */ static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) @@ -181,6 +186,7 @@ struct proto pingv6_prot = { .owner = THIS_MODULE, .init = ping_init_sock, .close = ping_close, + .destroy = ping_v6_destroy, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, .setsockopt = ipv6_setsockopt,

From: Maxim Mikityanskiy maximmi@nvidia.com

commit f6336724a4d4220c89a4ec38bca84b03b178b1a3 upstream.

tls_device_down takes a reference on all contexts it's going to move to the degraded state (software fallback). If sk_destruct runs afterwards, it can reduce the reference counter back to 1 and return early without destroying the context. Then tls_device_down will release the reference it took and call tls_device_free_ctx. However, the context will still stay in tls_device_down_list forever. The list will contain an item, memory for which is released, making a memory corruption possible.

Fix the above bug by properly removing the context from all lists before any call to tls_device_free_ctx.

Fixes: 3740651bf7e2 ("tls: Fix context leak on tls_device_down") Signed-off-by: Maxim Mikityanskiy maximmi@nvidia.com Reviewed-by: Tariq Toukan tariqt@nvidia.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/tls/tls_device.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)

--- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -1351,8 +1351,13 @@ static int tls_device_down(struct net_de * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW. * Now release the ref taken above. */ - if (refcount_dec_and_test(&ctx->refcount)) + if (refcount_dec_and_test(&ctx->refcount)) { + /* sk_destruct ran after tls_device_down took a ref, and + * it returned early. Complete the destruction here. + */ + list_del(&ctx->list); tls_device_free_ctx(ctx); + } }

up_write(&device_offload_lock);

From: Liang He windhl@126.com

[ Upstream commit ebbbe23fdf6070e31509638df3321688358cc211 ]

In bcm5421_init(), we should call of_node_put() for the reference returned by of_get_parent() which has increased the refcount.

Fixes: 3c326fe9cb7a ("[PATCH] ppc64: Add new PHY to sungem") Signed-off-by: Liang He windhl@126.com Link: https://lore.kernel.org/r/20220720131003.1287426-1-windhl@126.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/sungem_phy.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/drivers/net/sungem_phy.c b/drivers/net/sungem_phy.c index 4daac5fda073..0d40d265b688 100644 --- a/drivers/net/sungem_phy.c +++ b/drivers/net/sungem_phy.c @@ -454,6 +454,7 @@ static int bcm5421_init(struct mii_phy* phy) int can_low_power = 1; if (np == NULL || of_get_property(np, "no-autolowpower", NULL)) can_low_power = 0; + of_node_put(np); if (can_low_power) { /* Enable automatic low-power */ sungem_phy_write(phy, 0x1c, 0x9002);

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit e0bb4ab9dfddd872622239f49fb2bd403b70853b ]

While reading sysctl_tcp_min_tso_segs, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader.

Fixes: 95bd09eb2750 ("tcp: TSO packets automatic sizing") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 6a3adb0222f4..08466421e7e0 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1990,7 +1990,7 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now)

min_tso = ca_ops->min_tso_segs ? ca_ops->min_tso_segs(sk) : - sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs; + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);

tso_segs = tcp_tso_autosize(sk, mss_now, min_tso); return min_t(u32, tso_segs, sk->sk_gso_max_segs);

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit 1330ffacd05fc9ac4159d19286ce119e22450ed2 ]

While reading sysctl_tcp_min_rtt_wlen, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader.

Fixes: f672258391b4 ("tcp: track min RTT using windowed min-filter") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 78e16891f12b..f3b658fa3e7b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3058,7 +3058,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,

static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag) { - u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ; + u32 wlen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen) * HZ; struct tcp_sock *tp = tcp_sk(sk);

if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit 2afdbe7b8de84c28e219073a6661080e1b3ded48 ]

While reading sysctl_tcp_invalid_ratelimit, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader.

Fixes: 032ee4236954 ("tcp: helpers to mitigate ACK loops by rate-limiting out-of-window dupacks") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_input.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f3b658fa3e7b..db78197a44ff 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3581,7 +3581,8 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, if (*last_oow_ack_time) { s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);

- if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) { + if (0 <= elapsed && + elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) { NET_INC_STATS(net, mib_idx); return true; /* rate-limited: don't send yet! */ }

From: Sabrina Dubroca sd@queasysnail.net

[ Upstream commit f46040eeaf2e523a4096199fd93a11e794818009 ]

Commit 48ef50fa866a added a test on tb_sa[MACSEC_SA_ATTR_PN], but nothing guarantees that it's not NULL at this point. The same code was added to macsec_add_txsa, but there it's not a problem because validate_add_txsa checks that the MACSEC_SA_ATTR_PN attribute is present.

Note: it's not possible to reproduce with iproute, because iproute doesn't allow creating an SA without specifying the PN.

Fixes: 48ef50fa866a ("macsec: Netlink support of XPN cipher suites (IEEE 802.1AEbw)") Link: https://bugzilla.kernel.org/show_bug.cgi?id=208315 Reported-by: Frantisek Sumsal fsumsal@redhat.com Signed-off-by: Sabrina Dubroca sd@queasysnail.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/macsec.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 817577e713d7..769a1eca6bd8 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1753,7 +1753,8 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) }

pn_len = secy->xpn ? MACSEC_XPN_PN_LEN : MACSEC_DEFAULT_PN_LEN; - if (nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { + if (tb_sa[MACSEC_SA_ATTR_PN] && + nla_len(tb_sa[MACSEC_SA_ATTR_PN]) != pn_len) { pr_notice("macsec: nl: add_rxsa: bad pn length: %d != %d\n", nla_len(tb_sa[MACSEC_SA_ATTR_PN]), pn_len); rtnl_unlock();

From: Sabrina Dubroca sd@queasysnail.net

[ Upstream commit b07a0e2044057f201d694ab474f5c42a02b6465b ]

IEEE 802.1AEbw-2013 (section 10.7.8) specifies that the maximum value of the replay window is 2^30-1, to help with recovery of the upper bits of the PN.

To avoid leaving the existing macsec device in an inconsistent state if this test fails during changelink, reuse the cleanup mechanism introduced for HW offload. This wasn't needed until now because macsec_changelink_common could not fail during changelink, as modifying the cipher suite was not allowed.

Finally, this must happen after handling IFLA_MACSEC_CIPHER_SUITE so that secy->xpn is set.

Fixes: 48ef50fa866a ("macsec: Netlink support of XPN cipher suites (IEEE 802.1AEbw)") Signed-off-by: Sabrina Dubroca sd@queasysnail.net Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/macsec.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 634452d3ecc5..b3834e353c22 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -243,6 +243,7 @@ static struct macsec_cb *macsec_skb_cb(struct sk_buff *skb) #define DEFAULT_SEND_SCI true #define DEFAULT_ENCRYPT false #define DEFAULT_ENCODING_SA 0 +#define MACSEC_XPN_MAX_REPLAY_WINDOW (((1 << 30) - 1))

static bool send_sci(const struct macsec_secy *secy) { @@ -3746,9 +3747,6 @@ static int macsec_changelink_common(struct net_device *dev, secy->operational = tx_sa && tx_sa->active; }

- if (data[IFLA_MACSEC_WINDOW]) - secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]); - if (data[IFLA_MACSEC_ENCRYPT]) tx_sc->encrypt = !!nla_get_u8(data[IFLA_MACSEC_ENCRYPT]);

@@ -3794,6 +3792,16 @@ static int macsec_changelink_common(struct net_device *dev, } }

+ if (data[IFLA_MACSEC_WINDOW]) { + secy->replay_window = nla_get_u32(data[IFLA_MACSEC_WINDOW]); + + /* IEEE 802.1AEbw-2013 10.7.8 - maximum replay window + * for XPN cipher suites */ + if (secy->xpn && + secy->replay_window > MACSEC_XPN_MAX_REPLAY_WINDOW) + return -EINVAL; + } + return 0; }

@@ -3823,7 +3831,7 @@ static int macsec_changelink(struct net_device *dev, struct nlattr *tb[],

ret = macsec_changelink_common(dev, data); if (ret) - return ret; + goto cleanup;

/* If h/w offloading is available, propagate to the device */ if (macsec_is_offloaded(macsec)) {

From: Jianglei Nie niejianglei2021@163.com

[ Upstream commit c7b205fbbf3cffa374721bb7623f7aa8c46074f1 ]

init_rx_sa() allocates relevant resource for rx_sa->stats and rx_sa-> key.tfm with alloc_percpu() and macsec_alloc_tfm(). When some error occurs after init_rx_sa() is called in macsec_add_rxsa(), the function released rx_sa with kfree() without releasing rx_sa->stats and rx_sa-> key.tfm, which will lead to a resource leak.

We should call macsec_rxsa_put() instead of kfree() to decrease the ref count of rx_sa and release the relevant resource if the refcount is 0. The same bug exists in macsec_add_txsa() for tx_sa as well. This patch fixes the above two bugs.

Fixes: 3cf3227a21d1 ("net: macsec: hardware offloading infrastructure") Signed-off-by: Jianglei Nie niejianglei2021@163.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/macsec.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 95578f04f212..f354fad05714 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -1844,7 +1844,7 @@ static int macsec_add_rxsa(struct sk_buff *skb, struct genl_info *info) return 0;

cleanup: - kfree(rx_sa); + macsec_rxsa_put(rx_sa); rtnl_unlock(); return err; } @@ -2087,7 +2087,7 @@ static int macsec_add_txsa(struct sk_buff *skb, struct genl_info *info)

cleanup: secy->operational = was_operational; - kfree(tx_sa); + macsec_txsa_put(tx_sa); rtnl_unlock(); return err; }

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit 59bf6c65a09fff74215517aecffbbdcd67df76e3 ]

While reading sysctl_tcp_pacing_(ss|ca)_ratio, they can be changed concurrently. Thus, we need to add READ_ONCE() to their readers.

Fixes: 43e122b014c9 ("tcp: refine pacing rate determination") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_input.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index db78197a44ff..de066fad7dfe 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -910,9 +910,9 @@ static void tcp_update_pacing_rate(struct sock *sk) * end of slow start and should slow down. */ if (tcp_snd_cwnd(tp) < tp->snd_ssthresh / 2) - rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio; + rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio); else - rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio; + rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio);

rate *= max(tcp_snd_cwnd(tp), tp->packets_out);

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit 4866b2b0f7672b6d760c4b8ece6fb56f965dcc8a ]

While reading sysctl_tcp_comp_sack_delay_ns, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader.

Fixes: 6d82aa242092 ("tcp: add tcp_comp_sack_delay_ns sysctl") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_input.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index f09b1321a960..3591a25a8631 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5546,7 +5546,8 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) if (tp->srtt_us && tp->srtt_us < rtt) rtt = tp->srtt_us;

- delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns, + delay = min_t(unsigned long, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns), rtt * (NSEC_PER_USEC >> 3)/20); sock_hold(sk); hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay),

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit 79f55473bfc8ac51bd6572929a679eeb4da22251 ]

While reading sysctl_tcp_comp_sack_nr, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader.

Fixes: 9c21d2fc41c0 ("tcp: add tcp_comp_sack_nr sysctl") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 5de396075a27..9221c8c7b9a9 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5525,7 +5525,7 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) }

if (!tcp_is_sack(tp) || - tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr) + tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)) goto send_now;

if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit 96b9bd8c6d125490f9adfb57d387ef81a55a103e ]

While reading sysctl_fib_notify_on_flag_change, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers.

Fixes: 680aea08e78c ("net: ipv4: Emit notification when fib hardware flags are changed") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/fib_trie.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 43a496272227..c1b53854047b 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1042,6 +1042,7 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri)

void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) { + u8 fib_notify_on_flag_change; struct fib_alias *fa_match; struct sk_buff *skb; int err; @@ -1063,14 +1064,16 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) WRITE_ONCE(fa_match->offload, fri->offload); WRITE_ONCE(fa_match->trap, fri->trap);

+ fib_notify_on_flag_change = READ_ONCE(net->ipv4.sysctl_fib_notify_on_flag_change); + /* 2 means send notifications only if offload_failed was changed. */ - if (net->ipv4.sysctl_fib_notify_on_flag_change == 2 && + if (fib_notify_on_flag_change == 2 && READ_ONCE(fa_match->offload_failed) == fri->offload_failed) goto out;

WRITE_ONCE(fa_match->offload_failed, fri->offload_failed);

- if (!net->ipv4.sysctl_fib_notify_on_flag_change) + if (!fib_notify_on_flag_change) goto out;

skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC);

From: Vladimir Oltean vladimir.oltean@nxp.com

[ Upstream commit c7560d1203b7a1ea0b99a5c575547e95d564b2a8 ]

Due to an invalid conflict resolution on my side while working on 2 different series (LAG FDBs and FDB isolation), dsa_switch_do_lag_fdb_add() does not store the database associated with a dsa_mac_addr structure.

So after adding an FDB entry associated with a LAG, dsa_mac_addr_find() fails to find it while deleting it, because &a->db is zeroized memory for all stored FDB entries of lag->fdbs, and dsa_switch_do_lag_fdb_del() returns -ENOENT rather than deleting the entry.

Fixes: c26933639b54 ("net: dsa: request drivers to perform FDB isolation") Signed-off-by: Vladimir Oltean vladimir.oltean@nxp.com Link: https://lore.kernel.org/r/20220723012411.1125066-1-vladimir.oltean@nxp.com Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- net/dsa/switch.c | 1 + 1 file changed, 1 insertion(+)

diff --git a/net/dsa/switch.c b/net/dsa/switch.c index d8a80cf9742c..52f84ea349d2 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -363,6 +363,7 @@ static int dsa_switch_do_lag_fdb_add(struct dsa_switch *ds, struct dsa_lag *lag,

ether_addr_copy(a->addr, addr); a->vid = vid; + a->db = db; refcount_set(&a->refcount, 1); list_add_tail(&a->list, &lag->fdbs);

From: Sunil Goutham sgoutham@marvell.com

[ Upstream commit b354eaeec8637d87003945439209251d76a2bb95 ]

NIX_AF_TLXX_PIR/CIR register format has changed from OcteonTx2 to CN10K. CN10K supports larger burst size. Fix burst exponent and burst mantissa configuration for CN10K.

Also fixed 'maxrate' from u32 to u64 since 'police.rate_bytes_ps' passed by stack is also u64.

Fixes: e638a83f167e ("octeontx2-pf: TC_MATCHALL egress ratelimiting offload") Signed-off-by: Sunil Goutham sgoutham@marvell.com Signed-off-by: Subbaraya Sundeep sbhatta@marvell.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../ethernet/marvell/octeontx2/nic/otx2_tc.c | 76 ++++++++++++++----- 1 file changed, 55 insertions(+), 21 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c index a3d720b1b32c..e64318c110fd 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c @@ -28,6 +28,9 @@ #define MAX_RATE_EXPONENT 0x0FULL #define MAX_RATE_MANTISSA 0xFFULL

+#define CN10K_MAX_BURST_MANTISSA 0x7FFFULL +#define CN10K_MAX_BURST_SIZE 8453888ULL + /* Bitfields in NIX_TLX_PIR register */ #define TLX_RATE_MANTISSA GENMASK_ULL(8, 1) #define TLX_RATE_EXPONENT GENMASK_ULL(12, 9) @@ -35,6 +38,9 @@ #define TLX_BURST_MANTISSA GENMASK_ULL(36, 29) #define TLX_BURST_EXPONENT GENMASK_ULL(40, 37)

+#define CN10K_TLX_BURST_MANTISSA GENMASK_ULL(43, 29) +#define CN10K_TLX_BURST_EXPONENT GENMASK_ULL(47, 44) + struct otx2_tc_flow_stats { u64 bytes; u64 pkts; @@ -77,33 +83,42 @@ int otx2_tc_alloc_ent_bitmap(struct otx2_nic *nic) } EXPORT_SYMBOL(otx2_tc_alloc_ent_bitmap);

-static void otx2_get_egress_burst_cfg(u32 burst, u32 *burst_exp, - u32 *burst_mantissa) +static void otx2_get_egress_burst_cfg(struct otx2_nic *nic, u32 burst, + u32 *burst_exp, u32 *burst_mantissa) { + int max_burst, max_mantissa; unsigned int tmp;

+ if (is_dev_otx2(nic->pdev)) { + max_burst = MAX_BURST_SIZE; + max_mantissa = MAX_BURST_MANTISSA; + } else { + max_burst = CN10K_MAX_BURST_SIZE; + max_mantissa = CN10K_MAX_BURST_MANTISSA; + } + /* Burst is calculated as * ((256 + BURST_MANTISSA) << (1 + BURST_EXPONENT)) / 256 * Max supported burst size is 130,816 bytes. */ - burst = min_t(u32, burst, MAX_BURST_SIZE); + burst = min_t(u32, burst, max_burst); if (burst) { *burst_exp = ilog2(burst) ? ilog2(burst) - 1 : 0; tmp = burst - rounddown_pow_of_two(burst); - if (burst < MAX_BURST_MANTISSA) + if (burst < max_mantissa) *burst_mantissa = tmp * 2; else *burst_mantissa = tmp / (1ULL << (*burst_exp - 7)); } else { *burst_exp = MAX_BURST_EXPONENT; - *burst_mantissa = MAX_BURST_MANTISSA; + *burst_mantissa = max_mantissa; } }

-static void otx2_get_egress_rate_cfg(u32 maxrate, u32 *exp, +static void otx2_get_egress_rate_cfg(u64 maxrate, u32 *exp, u32 *mantissa, u32 *div_exp) { - unsigned int tmp; + u64 tmp;

/* Rate calculation by hardware * @@ -132,21 +147,44 @@ static void otx2_get_egress_rate_cfg(u32 maxrate, u32 *exp, } }

-static int otx2_set_matchall_egress_rate(struct otx2_nic *nic, u32 burst, u32 maxrate) +static u64 otx2_get_txschq_rate_regval(struct otx2_nic *nic, + u64 maxrate, u32 burst) { - struct otx2_hw *hw = &nic->hw; - struct nix_txschq_config *req; u32 burst_exp, burst_mantissa; u32 exp, mantissa, div_exp; + u64 regval = 0; + + /* Get exponent and mantissa values from the desired rate */ + otx2_get_egress_burst_cfg(nic, burst, &burst_exp, &burst_mantissa); + otx2_get_egress_rate_cfg(maxrate, &exp, &mantissa, &div_exp); + + if (is_dev_otx2(nic->pdev)) { + regval = FIELD_PREP(TLX_BURST_EXPONENT, (u64)burst_exp) | + FIELD_PREP(TLX_BURST_MANTISSA, (u64)burst_mantissa) | + FIELD_PREP(TLX_RATE_DIVIDER_EXPONENT, div_exp) | + FIELD_PREP(TLX_RATE_EXPONENT, exp) | + FIELD_PREP(TLX_RATE_MANTISSA, mantissa) | BIT_ULL(0); + } else { + regval = FIELD_PREP(CN10K_TLX_BURST_EXPONENT, (u64)burst_exp) | + FIELD_PREP(CN10K_TLX_BURST_MANTISSA, (u64)burst_mantissa) | + FIELD_PREP(TLX_RATE_DIVIDER_EXPONENT, div_exp) | + FIELD_PREP(TLX_RATE_EXPONENT, exp) | + FIELD_PREP(TLX_RATE_MANTISSA, mantissa) | BIT_ULL(0); + } + + return regval; +} + +static int otx2_set_matchall_egress_rate(struct otx2_nic *nic, + u32 burst, u64 maxrate) +{ + struct otx2_hw *hw = &nic->hw; + struct nix_txschq_config *req; int txschq, err;

/* All SQs share the same TL4, so pick the first scheduler */ txschq = hw->txschq_list[NIX_TXSCH_LVL_TL4][0];

- /* Get exponent and mantissa values from the desired rate */ - otx2_get_egress_burst_cfg(burst, &burst_exp, &burst_mantissa); - otx2_get_egress_rate_cfg(maxrate, &exp, &mantissa, &div_exp); - mutex_lock(&nic->mbox.lock); req = otx2_mbox_alloc_msg_nix_txschq_cfg(&nic->mbox); if (!req) { @@ -157,11 +195,7 @@ static int otx2_set_matchall_egress_rate(struct otx2_nic *nic, u32 burst, u32 ma req->lvl = NIX_TXSCH_LVL_TL4; req->num_regs = 1; req->reg[0] = NIX_AF_TL4X_PIR(txschq); - req->regval[0] = FIELD_PREP(TLX_BURST_EXPONENT, burst_exp) | - FIELD_PREP(TLX_BURST_MANTISSA, burst_mantissa) | - FIELD_PREP(TLX_RATE_DIVIDER_EXPONENT, div_exp) | - FIELD_PREP(TLX_RATE_EXPONENT, exp) | - FIELD_PREP(TLX_RATE_MANTISSA, mantissa) | BIT_ULL(0); + req->regval[0] = otx2_get_txschq_rate_regval(nic, maxrate, burst);

err = otx2_sync_mbox_msg(&nic->mbox); mutex_unlock(&nic->mbox.lock); @@ -230,7 +264,7 @@ static int otx2_tc_egress_matchall_install(struct otx2_nic *nic, struct netlink_ext_ack *extack = cls->common.extack; struct flow_action *actions = &cls->rule->action; struct flow_action_entry *entry; - u32 rate; + u64 rate; int err;

err = otx2_tc_validate_flow(nic, actions, extack); @@ -256,7 +290,7 @@ static int otx2_tc_egress_matchall_install(struct otx2_nic *nic, } /* Convert bytes per second to Mbps */ rate = entry->police.rate_bytes_ps * 8; - rate = max_t(u32, rate / 1000000, 1); + rate = max_t(u64, rate / 1000000, 1); err = otx2_set_matchall_egress_rate(nic, entry->police.burst, rate); if (err) return err;

From: Bart Van Assche bvanassche@acm.org

[ Upstream commit d1a7644648b7cdacaf8d1013a4285001911e9bc8 ]

Modify ufshcd_clear_cmd() such that it supports clearing multiple commands at once instead of one command at a time. This change will be used in a later patch to reduce the time spent in the reset handler.

Link: https://lore.kernel.org/r/20220613214442.212466-3-bvanassche@acm.org Reviewed-by: Stanley Chu stanley.chu@mediatek.com Reviewed-by: Adrian Hunter adrian.hunter@intel.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 | 42 ++++++++++++++++++++++++++------------- 1 file changed, 28 insertions(+), 14 deletions(-)

diff --git a/drivers/scsi/ufs/ufshcd.c b/drivers/scsi/ufs/ufshcd.c index 452ad0612067..a34c1fab0246 100644 --- a/drivers/scsi/ufs/ufshcd.c +++ b/drivers/scsi/ufs/ufshcd.c @@ -734,17 +734,28 @@ static enum utp_ocs ufshcd_get_tr_ocs(struct ufshcd_lrb *lrbp) }

/** - * ufshcd_utrl_clear - Clear a bit in UTRLCLR register + * ufshcd_utrl_clear() - Clear requests from the controller request list. * @hba: per adapter instance - * @pos: position of the bit to be cleared + * @mask: mask with one bit set for each request to be cleared */ -static inline void ufshcd_utrl_clear(struct ufs_hba *hba, u32 pos) +static inline void ufshcd_utrl_clear(struct ufs_hba *hba, u32 mask) { if (hba->quirks & UFSHCI_QUIRK_BROKEN_REQ_LIST_CLR) - ufshcd_writel(hba, (1 << pos), REG_UTP_TRANSFER_REQ_LIST_CLEAR); - else - ufshcd_writel(hba, ~(1 << pos), - REG_UTP_TRANSFER_REQ_LIST_CLEAR); + mask = ~mask; + /* + * From the UFSHCI specification: "UTP Transfer Request List CLear + * Register (UTRLCLR): This field is bit significant. Each bit + * corresponds to a slot in the UTP Transfer Request List, where bit 0 + * corresponds to request slot 0. A bit in this field is set to ‘0’ + * by host software to indicate to the host controller that a transfer + * request slot is cleared. The host controller + * shall free up any resources associated to the request slot + * immediately, and shall set the associated bit in UTRLDBR to ‘0’. The + * host software indicates no change to request slots by setting the + * associated bits in this field to ‘1’. Bits in this field shall only + * be set ‘1’ or ‘0’ by host software when UTRLRSR is set to ‘1’." + */ + ufshcd_writel(hba, ~mask, REG_UTP_TRANSFER_REQ_LIST_CLEAR); }

/** @@ -2853,16 +2864,19 @@ static int ufshcd_compose_dev_cmd(struct ufs_hba *hba, return ufshcd_compose_devman_upiu(hba, lrbp); }

-static int -ufshcd_clear_cmd(struct ufs_hba *hba, int tag) +/* + * Clear all the requests from the controller for which a bit has been set in + * @mask and wait until the controller confirms that these requests have been + * cleared. + */ +static int ufshcd_clear_cmds(struct ufs_hba *hba, u32 mask) { int err = 0; unsigned long flags; - u32 mask = 1 << tag;

/* clear outstanding transaction before retry */ spin_lock_irqsave(hba->host->host_lock, flags); - ufshcd_utrl_clear(hba, tag); + ufshcd_utrl_clear(hba, mask); spin_unlock_irqrestore(hba->host->host_lock, flags);

/* @@ -2953,7 +2967,7 @@ static int ufshcd_wait_for_dev_cmd(struct ufs_hba *hba, err = -ETIMEDOUT; dev_dbg(hba->dev, "%s: dev_cmd request timedout, tag %d\n", __func__, lrbp->task_tag); - if (!ufshcd_clear_cmd(hba, lrbp->task_tag)) + if (!ufshcd_clear_cmds(hba, 1U << lrbp->task_tag)) /* successfully cleared the command, retry if needed */ err = -EAGAIN; /* @@ -6988,7 +7002,7 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd) /* clear the commands that were pending for corresponding LUN */ for_each_set_bit(pos, &hba->outstanding_reqs, hba->nutrs) { if (hba->lrb[pos].lun == lun) { - err = ufshcd_clear_cmd(hba, pos); + err = ufshcd_clear_cmds(hba, 1U << pos); if (err) break; __ufshcd_transfer_req_compl(hba, 1U << pos); @@ -7090,7 +7104,7 @@ static int ufshcd_try_to_abort_task(struct ufs_hba *hba, int tag) goto out; }

- err = ufshcd_clear_cmd(hba, tag); + err = ufshcd_clear_cmds(hba, 1U << tag); if (err) dev_err(hba->dev, "%s: Failed clearing cmd at tag %d, err %d\n", __func__, tag, err);

From: Geliang Tang geliang.tang@suse.com

[ Upstream commit 1761fed2567807f26fbd53032ff622f55978c7a9 ]

When a bad checksum is detected and a single subflow is in use, don't send RST + MP_FAIL, send data_ack + MP_FAIL instead.

So invoke tcp_send_active_reset() only when mptcp_has_another_subflow() is true.

Signed-off-by: Geliang Tang geliang.tang@suse.com Signed-off-by: Mat Martineau mathew.j.martineau@linux.intel.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/mptcp/subflow.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 7919e259175d..ccae50eba664 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1221,14 +1221,14 @@ static bool subflow_check_data_avail(struct sock *ssk) /* RFC 8684 section 3.7. */ if (subflow->send_mp_fail) { if (mptcp_has_another_subflow(ssk)) { + ssk->sk_err = EBADMSG; + tcp_set_state(ssk, TCP_CLOSE); + subflow->reset_transient = 0; + subflow->reset_reason = MPTCP_RST_EMIDDLEBOX; + tcp_send_active_reset(ssk, GFP_ATOMIC); while ((skb = skb_peek(&ssk->sk_receive_queue))) sk_eat_skb(ssk, skb); } - ssk->sk_err = EBADMSG; - tcp_set_state(ssk, TCP_CLOSE); - subflow->reset_transient = 0; - subflow->reset_reason = MPTCP_RST_EMIDDLEBOX; - tcp_send_active_reset(ssk, GFP_ATOMIC); WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); return true; }

From: Jason Wang jasowang@redhat.com

[ Upstream commit 5a159128faff151b7fe5f4eb0f310b1e0a2d56bf ]

We try using cancel_delayed_work_sync() to prevent the work from enabling NAPI. This is insufficient since we don't disable the source of the refill work scheduling. This means an NAPI poll callback after cancel_delayed_work_sync() can schedule the refill work then can re-enable the NAPI that leads to use-after-free [1].

Since the work can enable NAPI, we can't simply disable NAPI before calling cancel_delayed_work_sync(). So fix this by introducing a dedicated boolean to control whether or not the work could be scheduled from NAPI.

[1] ================================================================== BUG: KASAN: use-after-free in refill_work+0x43/0xd4 Read of size 2 at addr ffff88810562c92e by task kworker/2:1/42

CPU: 2 PID: 42 Comm: kworker/2:1 Not tainted 5.19.0-rc1+ #480 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Workqueue: events refill_work Call Trace: <TASK> dump_stack_lvl+0x34/0x44 print_report.cold+0xbb/0x6ac ? _printk+0xad/0xde ? refill_work+0x43/0xd4 kasan_report+0xa8/0x130 ? refill_work+0x43/0xd4 refill_work+0x43/0xd4 process_one_work+0x43d/0x780 worker_thread+0x2a0/0x6f0 ? process_one_work+0x780/0x780 kthread+0x167/0x1a0 ? kthread_exit+0x50/0x50 ret_from_fork+0x22/0x30 </TASK> ...

Fixes: b2baed69e605c ("virtio_net: set/cancel work on ndo_open/ndo_stop") Signed-off-by: Jason Wang jasowang@redhat.com Acked-by: Michael S. Tsirkin mst@redhat.com Reviewed-by: Xuan Zhuo xuanzhuo@linux.alibaba.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/virtio_net.c | 37 ++++++++++++++++++++++++++++++++++--- 1 file changed, 34 insertions(+), 3 deletions(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index c7804fce204c..206904e60784 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -242,9 +242,15 @@ struct virtnet_info { /* Packet virtio header size */ u8 hdr_len;

- /* Work struct for refilling if we run low on memory. */ + /* Work struct for delayed refilling if we run low on memory. */ struct delayed_work refill;

+ /* Is delayed refill enabled? */ + bool refill_enabled; + + /* The lock to synchronize the access to refill_enabled */ + spinlock_t refill_lock; + /* Work struct for config space updates */ struct work_struct config_work;

@@ -348,6 +354,20 @@ static struct page *get_a_page(struct receive_queue *rq, gfp_t gfp_mask) return p; }

+static void enable_delayed_refill(struct virtnet_info *vi) +{ + spin_lock_bh(&vi->refill_lock); + vi->refill_enabled = true; + spin_unlock_bh(&vi->refill_lock); +} + +static void disable_delayed_refill(struct virtnet_info *vi) +{ + spin_lock_bh(&vi->refill_lock); + vi->refill_enabled = false; + spin_unlock_bh(&vi->refill_lock); +} + static void virtqueue_napi_schedule(struct napi_struct *napi, struct virtqueue *vq) { @@ -1527,8 +1547,12 @@ static int virtnet_receive(struct receive_queue *rq, int budget, }

if (rq->vq->num_free > min((unsigned int)budget, virtqueue_get_vring_size(rq->vq)) / 2) { - if (!try_fill_recv(vi, rq, GFP_ATOMIC)) - schedule_delayed_work(&vi->refill, 0); + if (!try_fill_recv(vi, rq, GFP_ATOMIC)) { + spin_lock(&vi->refill_lock); + if (vi->refill_enabled) + schedule_delayed_work(&vi->refill, 0); + spin_unlock(&vi->refill_lock); + } }

u64_stats_update_begin(&rq->stats.syncp); @@ -1651,6 +1675,8 @@ static int virtnet_open(struct net_device *dev) struct virtnet_info *vi = netdev_priv(dev); int i, err;

+ enable_delayed_refill(vi); + for (i = 0; i < vi->max_queue_pairs; i++) { if (i < vi->curr_queue_pairs) /* Make sure we have some buffers: if oom use wq. */ @@ -2033,6 +2059,8 @@ static int virtnet_close(struct net_device *dev) struct virtnet_info *vi = netdev_priv(dev); int i;

+ /* Make sure NAPI doesn't schedule refill work */ + disable_delayed_refill(vi); /* Make sure refill_work doesn't re-enable napi! */ cancel_delayed_work_sync(&vi->refill);

@@ -2792,6 +2820,8 @@ static int virtnet_restore_up(struct virtio_device *vdev)

virtio_device_ready(vdev);

+ enable_delayed_refill(vi); + if (netif_running(vi->dev)) { err = virtnet_open(vi->dev); if (err) @@ -3534,6 +3564,7 @@ static int virtnet_probe(struct virtio_device *vdev) vdev->priv = vi;

INIT_WORK(&vi->config_work, virtnet_config_changed_work); + spin_lock_init(&vi->refill_lock);

/* If we can receive ANY GSO packets, we must allocate large ones. */ if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||

From: Alejandro Lucero alejandro.lucero-palau@amd.com

[ Upstream commit 67c3b611d92fc238c43734878bc3e232ab570c79 ]

Sending a PTP packet can imply to use the normal TX driver datapath but invoked from the driver's ptp worker. The kernel generic TX code disables softirqs and preemption before calling specific driver TX code, but the ptp worker does not. Although current ptp driver functionality does not require it, there are several reasons for doing so:

1) The invoked code is always executed with softirqs disabled for non PTP packets. 2) Better if a ptp packet transmission is not interrupted by softirq handling which could lead to high latencies. 3) netdev_xmit_more used by the TX code requires preemption to be disabled.

Indeed a solution for dealing with kernel preemption state based on static kernel configuration is not possible since the introduction of dynamic preemption level configuration at boot time using the static calls functionality.

Fixes: f79c957a0b537 ("drivers: net: sfc: use netdev_xmit_more helper") Signed-off-by: Alejandro Lucero alejandro.lucero-palau@amd.com Link: https://lore.kernel.org/r/20220726064504.49613-1-alejandro.lucero-palau@amd.... Signed-off-by: Jakub Kicinski kuba@kernel.org Signed-off-by: Sasha Levin sashal@kernel.org --- drivers/net/ethernet/sfc/ptp.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+)

diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 4625f85acab2..10ad0b93d283 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -1100,7 +1100,29 @@ static void efx_ptp_xmit_skb_queue(struct efx_nic *efx, struct sk_buff *skb)

tx_queue = efx_channel_get_tx_queue(ptp_data->channel, type); if (tx_queue && tx_queue->timestamping) { + /* This code invokes normal driver TX code which is always + * protected from softirqs when called from generic TX code, + * which in turn disables preemption. Look at __dev_queue_xmit + * which uses rcu_read_lock_bh disabling preemption for RCU + * plus disabling softirqs. We do not need RCU reader + * protection here. + * + * Although it is theoretically safe for current PTP TX/RX code + * running without disabling softirqs, there are three good + * reasond for doing so: + * + * 1) The code invoked is mainly implemented for non-PTP + * packets and it is always executed with softirqs + * disabled. + * 2) This being a single PTP packet, better to not + * interrupt its processing by softirqs which can lead + * to high latencies. + * 3) netdev_xmit_more checks preemption is disabled and + * triggers a BUG_ON if not. + */ + local_bh_disable(); efx_enqueue_skb(tx_queue, skb); + local_bh_enable(); } else { WARN_ONCE(1, "PTP channel has no timestamped tx queue\n"); dev_kfree_skb_any(skb);

From: Dimitris Michailidis d.michailidis@fungible.com

[ Upstream commit 51a83391d77bb0f7ff0aef06ca4c7f5aa9e80b4c ]

The current implementation of fun_xdp_tx(), used for XPD_TX, is incorrect in that it takes an address/length pair and later releases it with page_frag_free(). It is OK for XDP_TX but the same code is used by ndo_xdp_xmit. In that case it loses the XDP memory type and releases the packet incorrectly for some of the types. Assorted breakage follows.

Change fun_xdp_tx() to take xdp_frame and rely on xdp_return_frame() in reclaim.

Fixes: db37bc177dae ("net/funeth: add the data path") Signed-off-by: Dimitris Michailidis dmichail@fungible.com Link: https://lore.kernel.org/r/20220726215923.7887-1-dmichail@fungible.com Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: Sasha Levin sashal@kernel.org --- .../net/ethernet/fungible/funeth/funeth_rx.c | 5 ++++- .../net/ethernet/fungible/funeth/funeth_tx.c | 20 +++++++++---------- .../ethernet/fungible/funeth/funeth_txrx.h | 6 +++--- 3 files changed, 16 insertions(+), 15 deletions(-)

diff --git a/drivers/net/ethernet/fungible/funeth/funeth_rx.c b/drivers/net/ethernet/fungible/funeth/funeth_rx.c index 0f6a549b9f67..29a6c2ede43a 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_rx.c +++ b/drivers/net/ethernet/fungible/funeth/funeth_rx.c @@ -142,6 +142,7 @@ static void *fun_run_xdp(struct funeth_rxq *q, skb_frag_t *frags, void *buf_va, int ref_ok, struct funeth_txq *xdp_q) { struct bpf_prog *xdp_prog; + struct xdp_frame *xdpf; struct xdp_buff xdp; u32 act;

@@ -163,7 +164,9 @@ static void *fun_run_xdp(struct funeth_rxq *q, skb_frag_t *frags, void *buf_va, case XDP_TX: if (unlikely(!ref_ok)) goto pass; - if (!fun_xdp_tx(xdp_q, xdp.data, xdp.data_end - xdp.data)) + + xdpf = xdp_convert_buff_to_frame(&xdp); + if (!xdpf || !fun_xdp_tx(xdp_q, xdpf)) goto xdp_error; FUN_QSTAT_INC(q, xdp_tx); q->xdp_flush |= FUN_XDP_FLUSH_TX; diff --git a/drivers/net/ethernet/fungible/funeth/funeth_tx.c b/drivers/net/ethernet/fungible/funeth/funeth_tx.c index ff6e29237253..2f6698b98b03 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_tx.c +++ b/drivers/net/ethernet/fungible/funeth/funeth_tx.c @@ -466,7 +466,7 @@ static unsigned int fun_xdpq_clean(struct funeth_txq *q, unsigned int budget)

do { fun_xdp_unmap(q, reclaim_idx); - page_frag_free(q->info[reclaim_idx].vaddr); + xdp_return_frame(q->info[reclaim_idx].xdpf);

trace_funeth_tx_free(q, reclaim_idx, 1, head);

@@ -479,11 +479,11 @@ static unsigned int fun_xdpq_clean(struct funeth_txq *q, unsigned int budget) return npkts; }

-bool fun_xdp_tx(struct funeth_txq *q, void *data, unsigned int len) +bool fun_xdp_tx(struct funeth_txq *q, struct xdp_frame *xdpf) { struct fun_eth_tx_req *req; struct fun_dataop_gl *gle; - unsigned int idx; + unsigned int idx, len; dma_addr_t dma;

if (fun_txq_avail(q) < FUN_XDP_CLEAN_THRES) @@ -494,7 +494,8 @@ bool fun_xdp_tx(struct funeth_txq *q, void *data, unsigned int len) return false; }

- dma = dma_map_single(q->dma_dev, data, len, DMA_TO_DEVICE); + len = xdpf->len; + dma = dma_map_single(q->dma_dev, xdpf->data, len, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(q->dma_dev, dma))) { FUN_QSTAT_INC(q, tx_map_err); return false; @@ -514,7 +515,7 @@ bool fun_xdp_tx(struct funeth_txq *q, void *data, unsigned int len) gle = (struct fun_dataop_gl *)req->dataop.imm; fun_dataop_gl_init(gle, 0, 0, len, dma);

- q->info[idx].vaddr = data; + q->info[idx].xdpf = xdpf;

u64_stats_update_begin(&q->syncp); q->stats.tx_bytes += len; @@ -545,12 +546,9 @@ int fun_xdp_xmit_frames(struct net_device *dev, int n, if (unlikely(q_idx >= fp->num_xdpqs)) return -ENXIO;

- for (q = xdpqs[q_idx], i = 0; i < n; i++) { - const struct xdp_frame *xdpf = frames[i]; - - if (!fun_xdp_tx(q, xdpf->data, xdpf->len)) + for (q = xdpqs[q_idx], i = 0; i < n; i++) + if (!fun_xdp_tx(q, frames[i])) break; - }

if (unlikely(flags & XDP_XMIT_FLUSH)) fun_txq_wr_db(q); @@ -577,7 +575,7 @@ static void fun_xdpq_purge(struct funeth_txq *q) unsigned int idx = q->cons_cnt & q->mask;

fun_xdp_unmap(q, idx); - page_frag_free(q->info[idx].vaddr); + xdp_return_frame(q->info[idx].xdpf); q->cons_cnt++; } } diff --git a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h index 04c9f91b7489..8708e2895946 100644 --- a/drivers/net/ethernet/fungible/funeth/funeth_txrx.h +++ b/drivers/net/ethernet/fungible/funeth/funeth_txrx.h @@ -95,8 +95,8 @@ struct funeth_txq_stats { /* per Tx queue SW counters */

struct funeth_tx_info { /* per Tx descriptor state */ union { - struct sk_buff *skb; /* associated packet */ - void *vaddr; /* start address for XDP */ + struct sk_buff *skb; /* associated packet (sk_buff path) */ + struct xdp_frame *xdpf; /* associated XDP frame (XDP path) */ }; };

@@ -245,7 +245,7 @@ static inline int fun_irq_node(const struct fun_irq *p) int fun_rxq_napi_poll(struct napi_struct *napi, int budget); int fun_txq_napi_poll(struct napi_struct *napi, int budget); netdev_tx_t fun_start_xmit(struct sk_buff *skb, struct net_device *netdev); -bool fun_xdp_tx(struct funeth_txq *q, void *data, unsigned int len); +bool fun_xdp_tx(struct funeth_txq *q, struct xdp_frame *xdpf); int fun_xdp_xmit_frames(struct net_device *dev, int n, struct xdp_frame **frames, u32 flags);

From: Ralph Campbell rcampbell@nvidia.com

commit 8a295dbbaf7292c582a40ce469c326f472d51f66 upstream.

If hmm_range_fault() is called with the HMM_PFN_REQ_FAULT flag and a device private PTE is found, the hmm_range::dev_private_owner page is used to determine if the device private page should not be faulted in. However, if the device private page is not owned by the caller, hmm_range_fault() returns an error instead of calling migrate_to_ram() to fault in the page.

For example, if a page is migrated to GPU private memory and a RDMA fault capable NIC tries to read the migrated page, without this patch it will get an error. With this patch, the page will be migrated back to system memory and the NIC will be able to read the data.

Link: https://lkml.kernel.org/r/20220727000837.4128709-2-rcampbell@nvidia.com Link: https://lkml.kernel.org/r/20220725183615.4118795-2-rcampbell@nvidia.com Fixes: 08ddddda667b ("mm/hmm: check the device private page owner in hmm_range_fault()") Signed-off-by: Ralph Campbell rcampbell@nvidia.com Reported-by: Felix Kuehling felix.kuehling@amd.com Reviewed-by: Alistair Popple apopple@nvidia.com Cc: Philip Yang Philip.Yang@amd.com Cc: Jason Gunthorpe jgg@nvidia.com Cc: stable@vger.kernel.org Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- mm/hmm.c | 19 ++++++++----------- 1 file changed, 8 insertions(+), 11 deletions(-)

--- a/mm/hmm.c +++ b/mm/hmm.c @@ -212,14 +212,6 @@ int hmm_vma_handle_pmd(struct mm_walk *w unsigned long end, unsigned long hmm_pfns[], pmd_t pmd); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */

-static inline bool hmm_is_device_private_entry(struct hmm_range *range, - swp_entry_t entry) -{ - return is_device_private_entry(entry) && - pfn_swap_entry_to_page(entry)->pgmap->owner == - range->dev_private_owner; -} - static inline unsigned long pte_to_hmm_pfn_flags(struct hmm_range *range, pte_t pte) { @@ -252,10 +244,12 @@ static int hmm_vma_handle_pte(struct mm_ swp_entry_t entry = pte_to_swp_entry(pte);

/* - * Never fault in device private pages, but just report - * the PFN even if not present. + * Don't fault in device private pages owned by the caller, + * just report the PFN. */ - if (hmm_is_device_private_entry(range, entry)) { + if (is_device_private_entry(entry) && + pfn_swap_entry_to_page(entry)->pgmap->owner == + range->dev_private_owner) { cpu_flags = HMM_PFN_VALID; if (is_writable_device_private_entry(entry)) cpu_flags |= HMM_PFN_WRITE; @@ -273,6 +267,9 @@ static int hmm_vma_handle_pte(struct mm_ if (!non_swap_entry(entry)) goto fault;

+ if (is_device_private_entry(entry)) + goto fault; + if (is_device_exclusive_entry(entry)) goto fault;

From: Kuniyuki Iwashima kuniyu@amazon.com

[ Upstream commit 0f1e4d06591d0a7907c71f7b6d1c79f8a4de8098 ]

While reading sysctl_tcp_workaround_signed_windows, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers.

Fixes: 15d99e02baba ("[TCP]: sysctl to allow TCP window > 32767 sans wscale") Signed-off-by: Kuniyuki Iwashima kuniyu@amazon.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Sasha Levin sashal@kernel.org --- net/ipv4/tcp_output.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 66836b8bd46f..a7f0a1f0c2a3 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -227,7 +227,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, * which we interpret as a sign the remote TCP is not * misinterpreting the window field as a signed quantity. */ - if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows) + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)) (*rcv_wnd) = min(space, MAX_TCP_WINDOW); else (*rcv_wnd) = min_t(u32, space, U16_MAX); @@ -282,7 +282,7 @@ static u16 tcp_select_window(struct sock *sk) * scaled window. */ if (!tp->rx_opt.rcv_wscale && - sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows) + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)) new_win = min(new_win, MAX_TCP_WINDOW); else new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));

From: Toshi Kani toshi.kani@hpe.com

commit 5e2805d5379619c4a2e3ae4994e73b36439f4bad upstream.

The commit

cb51a371d08e ("EDAC/ghes: Setup DIMM label from DMI and use it in error reports")

enforced that both the bank and device strings passed to dimm_setup_label() are not NULL.

However, there are BIOSes, for example on a

HPE ProLiant DL360 Gen10/ProLiant DL360 Gen10, BIOS U32 03/15/2019

which don't populate both strings:

Handle 0x0020, DMI type 17, 84 bytes Memory Device Array Handle: 0x0013 Error Information Handle: Not Provided Total Width: 72 bits Data Width: 64 bits Size: 32 GB Form Factor: DIMM Set: None Locator: PROC 1 DIMM 1 <===== device Bank Locator: Not Specified <===== bank

This results in a buffer overflow because ghes_edac_register() calls strlen() on an uninitialized label, which had non-zero values left over from krealloc_array():

detected buffer overflow in __fortify_strlen ------------[ cut here ]------------ kernel BUG at lib/string_helpers.c:983! invalid opcode: 0000 [#1] PREEMPT SMP NOPTI CPU: 1 PID: 1 Comm: swapper/0 Tainted: G I 5.18.6-200.fc36.x86_64 #1 Hardware name: HPE ProLiant DL360 Gen10/ProLiant DL360 Gen10, BIOS U32 03/15/2019 RIP: 0010:fortify_panic ... Call Trace: <TASK> ghes_edac_register.cold ghes_probe platform_probe really_probe __driver_probe_device driver_probe_device __driver_attach ? __device_attach_driver bus_for_each_dev bus_add_driver driver_register acpi_ghes_init acpi_init ? acpi_sleep_proc_init do_one_initcall

The label contains garbage because the commit in Fixes reallocs the DIMMs array while scanning the system but doesn't clear the newly allocated memory.

Change dimm_setup_label() to always initialize the label to fix the issue. Set it to the empty string in case BIOS does not provide both bank and device so that ghes_edac_register() can keep the default label given by edac_mc_alloc_dimms().

[ bp: Rewrite commit message. ]

Fixes: b9cae27728d1f ("EDAC/ghes: Scan the system once on driver init") Co-developed-by: Robert Richter rric@kernel.org Signed-off-by: Robert Richter rric@kernel.org Signed-off-by: Toshi Kani toshi.kani@hpe.com Signed-off-by: Borislav Petkov bp@suse.de Tested-by: Robert Elliott elliott@hpe.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220719220124.760359-1-toshi.kani@hpe.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/edac/ghes_edac.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-)

--- a/drivers/edac/ghes_edac.c +++ b/drivers/edac/ghes_edac.c @@ -101,9 +101,14 @@ static void dimm_setup_label(struct dimm

dmi_memdev_name(handle, &bank, &device);

- /* both strings must be non-zero */ - if (bank && *bank && device && *device) - snprintf(dimm->label, sizeof(dimm->label), "%s %s", bank, device); + /* + * Set to a NULL string when both bank and device are zero. In this case, + * the label assigned by default will be preserved. + */ + snprintf(dimm->label, sizeof(dimm->label), "%s%s%s", + (bank && *bank) ? bank : "", + (bank && *bank && device && *device) ? " " : "", + (device && *device) ? device : ""); }

static void assign_dmi_dimm_info(struct dimm_info *dimm, struct memdev_dmi_entry *entry)

From: Sherry Sun sherry.sun@nxp.com

commit 4bcffe941758ee17becb43af3b25487f848f6512 upstream.

zynqmp_get_error_info() writes 0 to the ECC_CLR_OFST register after an interrupt for a {un-,}correctable error is raised, which disables the error interrupts. Then the interrupt handler will be called only once. Therefore, re-enable the error interrupt line at the end of intr_handler() for v3.x Synopsys EDAC DDR.

Fixes: f7824ded4149 ("EDAC/synopsys: Add support for version 3 of the Synopsys EDAC DDR") Signed-off-by: Sherry Sun sherry.sun@nxp.com Signed-off-by: Borislav Petkov bp@suse.de Reviewed-by: Shubhrajyoti Datta Shubhrajyoti.datta@xilinx.com Acked-by: Michal Simek michal.simek@xilinx.com Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20220427015137.8406-3-sherry.sun@nxp.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- drivers/edac/synopsys_edac.c | 47 ++++++++++++++++++++++--------------------- 1 file changed, 25 insertions(+), 22 deletions(-)

--- a/drivers/edac/synopsys_edac.c +++ b/drivers/edac/synopsys_edac.c @@ -527,6 +527,28 @@ static void handle_error(struct mem_ctl_ memset(p, 0, sizeof(*p)); }

+static void enable_intr(struct synps_edac_priv *priv) +{ + /* Enable UE/CE Interrupts */ + if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR) + writel(DDR_UE_MASK | DDR_CE_MASK, + priv->baseaddr + ECC_CLR_OFST); + else + writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK, + priv->baseaddr + DDR_QOS_IRQ_EN_OFST); + +} + +static void disable_intr(struct synps_edac_priv *priv) +{ + /* Disable UE/CE Interrupts */ + if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR) + writel(0x0, priv->baseaddr + ECC_CLR_OFST); + else + writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK, + priv->baseaddr + DDR_QOS_IRQ_DB_OFST); +} + /** * intr_handler - Interrupt Handler for ECC interrupts. * @irq: IRQ number. @@ -568,6 +590,9 @@ static irqreturn_t intr_handler(int irq, /* v3.0 of the controller does not have this register */ if (!(priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR)) writel(regval, priv->baseaddr + DDR_QOS_IRQ_STAT_OFST); + else + enable_intr(priv); + return IRQ_HANDLED; }

@@ -850,28 +875,6 @@ static void mc_init(struct mem_ctl_info init_csrows(mci); }

-static void enable_intr(struct synps_edac_priv *priv) -{ - /* Enable UE/CE Interrupts */ - if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR) - writel(DDR_UE_MASK | DDR_CE_MASK, - priv->baseaddr + ECC_CLR_OFST); - else - writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK, - priv->baseaddr + DDR_QOS_IRQ_EN_OFST); - -} - -static void disable_intr(struct synps_edac_priv *priv) -{ - /* Disable UE/CE Interrupts */ - if (priv->p_data->quirks & DDR_ECC_INTR_SELF_CLEAR) - writel(0x0, priv->baseaddr + ECC_CLR_OFST); - else - writel(DDR_QOSUE_MASK | DDR_QOSCE_MASK, - priv->baseaddr + DDR_QOS_IRQ_DB_OFST); -} - static int setup_irq(struct mem_ctl_info *mci, struct platform_device *pdev) {

From: Waiman Long longman@redhat.com

commit 6eebd5fb20838f5971ba17df9f55cc4f84a31053 upstream.

With commit d257cc8cb8d5 ("locking/rwsem: Make handoff bit handling more consistent"), the writer that sets the handoff bit can be interrupted out without clearing the bit if the wait queue isn't empty. This disables reader and writer optimistic lock spinning and stealing.

Now if a non-first writer in the queue is somehow woken up or a new waiter enters the slowpath, it can't acquire the lock. This is not the case before commit d257cc8cb8d5 as the writer that set the handoff bit will clear it when exiting out via the out_nolock path. This is less efficient as the busy rwsem stays in an unlock state for a longer time.

In some cases, this new behavior may cause lockups as shown in [1] and [2].

This patch allows a non-first writer to ignore the handoff bit if it is not originally set or initiated by the first waiter. This patch is shown to be effective in fixing the lockup problem reported in [1].

[1] https://lore.kernel.org/lkml/20220617134325.GC30825@techsingularity.net/ [2] https://lore.kernel.org/lkml/3f02975c-1a9d-be20-32cf-f1d8e3dfafcc@oracle.com...

Fixes: d257cc8cb8d5 ("locking/rwsem: Make handoff bit handling more consistent") Signed-off-by: Waiman Long longman@redhat.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Acked-by: John Donnelly john.p.donnelly@oracle.com Tested-by: Mel Gorman mgorman@techsingularity.net Link: https://lore.kernel.org/r/20220622200419.778799-1-longman@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- kernel/locking/rwsem.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-)

--- a/kernel/locking/rwsem.c +++ b/kernel/locking/rwsem.c @@ -334,8 +334,6 @@ struct rwsem_waiter { struct task_struct *task; enum rwsem_waiter_type type; unsigned long timeout; - - /* Writer only, not initialized in reader */ bool handoff_set; }; #define rwsem_first_waiter(sem) \ @@ -455,10 +453,12 @@ static void rwsem_mark_wake(struct rw_se * to give up the lock), request a HANDOFF to * force the issue. */ - if (!(oldcount & RWSEM_FLAG_HANDOFF) && - time_after(jiffies, waiter->timeout)) { - adjustment -= RWSEM_FLAG_HANDOFF; - lockevent_inc(rwsem_rlock_handoff); + if (time_after(jiffies, waiter->timeout)) { + if (!(oldcount & RWSEM_FLAG_HANDOFF)) { + adjustment -= RWSEM_FLAG_HANDOFF; + lockevent_inc(rwsem_rlock_handoff); + } + waiter->handoff_set = true; }

atomic_long_add(-adjustment, &sem->count); @@ -568,7 +568,7 @@ static void rwsem_mark_wake(struct rw_se static inline bool rwsem_try_write_lock(struct rw_semaphore *sem, struct rwsem_waiter *waiter) { - bool first = rwsem_first_waiter(sem) == waiter; + struct rwsem_waiter *first = rwsem_first_waiter(sem); long count, new;

lockdep_assert_held(&sem->wait_lock); @@ -578,11 +578,20 @@ static inline bool rwsem_try_write_lock( bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);

if (has_handoff) { - if (!first) + /* + * Honor handoff bit and yield only when the first + * waiter is the one that set it. Otherwisee, we + * still try to acquire the rwsem. + */ + if (first->handoff_set && (waiter != first)) return false;

- /* First waiter inherits a previously set handoff bit */ - waiter->handoff_set = true; + /* + * First waiter can inherit a previously set handoff + * bit and spin on rwsem if lock acquisition fails. + */ + if (waiter == first) + waiter->handoff_set = true; }

new = count; @@ -972,6 +981,7 @@ queue: waiter.task = current; waiter.type = RWSEM_WAITING_FOR_READ; waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT; + waiter.handoff_set = false;

raw_spin_lock_irq(&sem->wait_lock); if (list_empty(&sem->wait_list)) {