6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Christoph Hellwig <hch(a)lst.de>
commit e003f74afbd2feadbb9ffbf9135e2d2fb5d320a5 upstream.
Factor out a helper that calls filemap_write_and_wait_range and
invalidate_inode_pages2_range for the range covered by a write kiocb or
returns -EAGAIN if the kiocb is marked as nowait and there would be pages
to write or invalidate.
Link: https://lkml.kernel.org/r/20230601145904.1385409-6-hch@lst.de
Signed-off-by: Christoph Hellwig <hch(a)lst.de>
Reviewed-by: Damien Le Moal <dlemoal(a)kernel.org>
Reviewed-by: Hannes Reinecke <hare(a)suse.de>
Acked-by: Darrick J. Wong <djwong(a)kernel.org>
Cc: Al Viro <viro(a)zeniv.linux.org.uk>
Cc: Andreas Gruenbacher <agruenba(a)redhat.com>
Cc: Anna Schumaker <anna(a)kernel.org>
Cc: Chao Yu <chao(a)kernel.org>
Cc: Christian Brauner <brauner(a)kernel.org>
Cc: Ilya Dryomov <idryomov(a)gmail.com>
Cc: Jaegeuk Kim <jaegeuk(a)kernel.org>
Cc: Jens Axboe <axboe(a)kernel.dk>
Cc: Johannes Thumshirn <johannes.thumshirn(a)wdc.com>
Cc: Matthew Wilcox <willy(a)infradead.org>
Cc: Miklos Szeredi <miklos(a)szeredi.hu>
Cc: Miklos Szeredi <mszeredi(a)redhat.com>
Cc: Theodore Ts'o <tytso(a)mit.edu>
Cc: Trond Myklebust <trond.myklebust(a)hammerspace.com>
Cc: Xiubo Li <xiubli(a)redhat.com>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
Signed-off-by: Mahmoud Adam <mngyadam(a)amazon.de>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
include/linux/pagemap.h | 1 +
mm/filemap.c | 48 ++++++++++++++++++++++++++++--------------------
2 files changed, 29 insertions(+), 20 deletions(-)
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -30,6 +30,7 @@ static inline void invalidate_remote_ino
int invalidate_inode_pages2(struct address_space *mapping);
int invalidate_inode_pages2_range(struct address_space *mapping,
pgoff_t start, pgoff_t end);
+int kiocb_invalidate_pages(struct kiocb *iocb, size_t count);
int write_inode_now(struct inode *, int sync);
int filemap_fdatawrite(struct address_space *);
int filemap_flush(struct address_space *);
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2839,6 +2839,33 @@ put_folios:
}
EXPORT_SYMBOL_GPL(filemap_read);
+int kiocb_invalidate_pages(struct kiocb *iocb, size_t count)
+{
+ struct address_space *mapping = iocb->ki_filp->f_mapping;
+ loff_t pos = iocb->ki_pos;
+ loff_t end = pos + count - 1;
+ int ret;
+
+ if (iocb->ki_flags & IOCB_NOWAIT) {
+ /* we could block if there are any pages in the range */
+ if (filemap_range_has_page(mapping, pos, end))
+ return -EAGAIN;
+ } else {
+ ret = filemap_write_and_wait_range(mapping, pos, end);
+ if (ret)
+ return ret;
+ }
+
+ /*
+ * After a write we want buffered reads to be sure to go to disk to get
+ * the new data. We invalidate clean cached page from the region we're
+ * about to write. We do this *before* the write so that we can return
+ * without clobbering -EIOCBQUEUED from ->direct_IO().
+ */
+ return invalidate_inode_pages2_range(mapping, pos >> PAGE_SHIFT,
+ end >> PAGE_SHIFT);
+}
+
/**
* generic_file_read_iter - generic filesystem read routine
* @iocb: kernel I/O control block
@@ -3737,30 +3764,11 @@ generic_file_direct_write(struct kiocb *
write_len = iov_iter_count(from);
end = (pos + write_len - 1) >> PAGE_SHIFT;
- if (iocb->ki_flags & IOCB_NOWAIT) {
- /* If there are pages to writeback, return */
- if (filemap_range_has_page(file->f_mapping, pos,
- pos + write_len - 1))
- return -EAGAIN;
- } else {
- written = filemap_write_and_wait_range(mapping, pos,
- pos + write_len - 1);
- if (written)
- goto out;
- }
-
- /*
- * After a write we want buffered reads to be sure to go to disk to get
- * the new data. We invalidate clean cached page from the region we're
- * about to write. We do this *before* the write so that we can return
- * without clobbering -EIOCBQUEUED from ->direct_IO().
- */
- written = invalidate_inode_pages2_range(mapping,
- pos >> PAGE_SHIFT, end);
/*
* If a page can not be invalidated, return 0 to fall back
* to buffered write.
*/
+ written = kiocb_invalidate_pages(iocb, write_len);
if (written) {
if (written == -EBUSY)
return 0;
6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: K Prateek Nayak <kprateek.nayak(a)amd.com>
[ Upstream commit c26fabe73330d983c7ce822c6b6ec0879b4da61f ]
Until commit 5c2712387d48 ("cacheinfo: Fix LLC is not exported through
sysfs"), cacheinfo called populate_cache_leaves() for CPU coming online
which let the arch specific functions handle (at least on x86)
populating the shared_cpu_map. However, with the changes in the
aforementioned commit, populate_cache_leaves() is not called when a CPU
comes online as a result of hotplug since last_level_cache_is_valid()
returns true as the cacheinfo data is not discarded. The CPU coming
online is not present in shared_cpu_map, however, it will not be added
since the cpu_cacheinfo->cpu_map_populated flag is set (it is set in
populate_cache_leaves() when cacheinfo is first populated for x86)
This can lead to inconsistencies in the shared_cpu_map when an offlined
CPU comes online again. Example below depicts the inconsistency in the
shared_cpu_list in cacheinfo when CPU8 is offlined and onlined again on
a 3rd Generation EPYC processor:
# for i in /sys/devices/system/cpu/cpu8/cache/index*/shared_cpu_list; do echo -n "$i: "; cat $i; done
/sys/devices/system/cpu/cpu8/cache/index0/shared_cpu_list: 8,136
/sys/devices/system/cpu/cpu8/cache/index1/shared_cpu_list: 8,136
/sys/devices/system/cpu/cpu8/cache/index2/shared_cpu_list: 8,136
/sys/devices/system/cpu/cpu8/cache/index3/shared_cpu_list: 8-15,136-143
# echo 0 > /sys/devices/system/cpu/cpu8/online
# echo 1 > /sys/devices/system/cpu/cpu8/online
# for i in /sys/devices/system/cpu/cpu8/cache/index*/shared_cpu_list; do echo -n "$i: "; cat $i; done
/sys/devices/system/cpu/cpu8/cache/index0/shared_cpu_list: 8
/sys/devices/system/cpu/cpu8/cache/index1/shared_cpu_list: 8
/sys/devices/system/cpu/cpu8/cache/index2/shared_cpu_list: 8
/sys/devices/system/cpu/cpu8/cache/index3/shared_cpu_list: 8
# cat /sys/devices/system/cpu/cpu136/cache/index0/shared_cpu_list
136
# cat /sys/devices/system/cpu/cpu136/cache/index3/shared_cpu_list
9-15,136-143
Clear the flag when the CPU is removed from shared_cpu_map when
cache_shared_cpu_map_remove() is called during CPU hotplug. This will
allow cache_shared_cpu_map_setup() to add the CPU coming back online in
the shared_cpu_map. Set the flag again when the shared_cpu_map is setup.
Following are results of performing the same test as described above with
the changes:
# for i in /sys/devices/system/cpu/cpu8/cache/index*/shared_cpu_list; do echo -n "$i: "; cat $i; done
/sys/devices/system/cpu/cpu8/cache/index0/shared_cpu_list: 8,136
/sys/devices/system/cpu/cpu8/cache/index1/shared_cpu_list: 8,136
/sys/devices/system/cpu/cpu8/cache/index2/shared_cpu_list: 8,136
/sys/devices/system/cpu/cpu8/cache/index3/shared_cpu_list: 8-15,136-143
# echo 0 > /sys/devices/system/cpu/cpu8/online
# echo 1 > /sys/devices/system/cpu/cpu8/online
# for i in /sys/devices/system/cpu/cpu8/cache/index*/shared_cpu_list; do echo -n "$i: "; cat $i; done
/sys/devices/system/cpu/cpu8/cache/index0/shared_cpu_list: 8,136
/sys/devices/system/cpu/cpu8/cache/index1/shared_cpu_list: 8,136
/sys/devices/system/cpu/cpu8/cache/index2/shared_cpu_list: 8,136
/sys/devices/system/cpu/cpu8/cache/index3/shared_cpu_list: 8-15,136-143
# cat /sys/devices/system/cpu/cpu136/cache/index0/shared_cpu_list
8,136
# cat /sys/devices/system/cpu/cpu136/cache/index3/shared_cpu_list
8-15,136-143
Fixes: 5c2712387d48 ("cacheinfo: Fix LLC is not exported through sysfs")
Signed-off-by: K Prateek Nayak <kprateek.nayak(a)amd.com>
Reviewed-by: Yicong Yang <yangyicong(a)hisilicon.com>
Reviewed-by: Sudeep Holla <sudeep.holla(a)arm.com>
Link: https://lore.kernel.org/r/20230508084115.1157-3-kprateek.nayak@amd.com
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Signed-off-by: Wen Yang <wen.yang(a)linux.dev>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/base/cacheinfo.c | 6 ++++++
1 file changed, 6 insertions(+)
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -365,11 +365,14 @@ static int cache_shared_cpu_map_setup(un
coherency_max_size = this_leaf->coherency_line_size;
}
+ /* shared_cpu_map is now populated for the cpu */
+ this_cpu_ci->cpu_map_populated = true;
return 0;
}
static void cache_shared_cpu_map_remove(unsigned int cpu)
{
+ struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
struct cacheinfo *this_leaf, *sib_leaf;
unsigned int sibling, index, sib_index;
@@ -404,6 +407,9 @@ static void cache_shared_cpu_map_remove(
if (of_have_populated_dt())
of_node_put(this_leaf->fw_token);
}
+
+ /* cpu is no longer populated in the shared map */
+ this_cpu_ci->cpu_map_populated = false;
}
static void free_cache_attributes(unsigned int cpu)
6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Yicong Yang <yangyicong(a)hisilicon.com>
[ Upstream commit 5c2712387d4850e0b64121d5fd3e6c4e84ea3266 ]
After entering 6.3-rc1 the LLC cacheinfo is not exported on our ACPI
based arm64 server. This is because the LLC cacheinfo is partly reset
when secondary CPUs boot up. On arm64 the primary cpu will allocate
and setup cacheinfo:
init_cpu_topology()
for_each_possible_cpu()
fetch_cache_info() // Allocate cacheinfo and init levels
detect_cache_attributes()
cache_shared_cpu_map_setup()
if (!last_level_cache_is_valid()) // not valid, setup LLC
cache_setup_properties() // setup LLC
On secondary CPU boot up:
detect_cache_attributes()
populate_cache_leaves()
get_cache_type() // Get cache type from clidr_el1,
// for LLC type=CACHE_TYPE_NOCACHE
cache_shared_cpu_map_setup()
if (!last_level_cache_is_valid()) // Valid and won't go to this branch,
// leave LLC's type=CACHE_TYPE_NOCACHE
The last_level_cache_is_valid() use cacheinfo->{attributes, fw_token} to
test it's valid or not, but populate_cache_leaves() will only reset
LLC's type, so we won't try to re-setup LLC's type and leave it
CACHE_TYPE_NOCACHE and won't export it through sysfs.
This patch tries to fix this by not re-populating the cache leaves if
the LLC is valid.
Fixes: 5944ce092b97 ("arch_topology: Build cacheinfo from primary CPU")
Signed-off-by: Yicong Yang <yangyicong(a)hisilicon.com>
Reviewed-by: Pierre Gondois <pierre.gondois(a)arm.com>
Reviewed-by: Sudeep Holla <sudeep.holla(a)arm.com>
Link: https://lore.kernel.org/r/20230328114915.33340-1-yangyicong@huawei.com
Signed-off-by: Wen Yang <wen.yang(a)linux.dev>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/base/cacheinfo.c | 16 +++++++++++-----
1 file changed, 11 insertions(+), 5 deletions(-)
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -490,12 +490,18 @@ int detect_cache_attributes(unsigned int
populate_leaves:
/*
- * populate_cache_leaves() may completely setup the cache leaves and
- * shared_cpu_map or it may leave it partially setup.
+ * If LLC is valid the cache leaves were already populated so just go to
+ * update the cpu map.
*/
- ret = populate_cache_leaves(cpu);
- if (ret)
- goto free_ci;
+ if (!last_level_cache_is_valid(cpu)) {
+ /*
+ * populate_cache_leaves() may completely setup the cache leaves and
+ * shared_cpu_map or it may leave it partially setup.
+ */
+ ret = populate_cache_leaves(cpu);
+ if (ret)
+ goto free_ci;
+ }
/*
* For systems using DT for cache hierarchy, fw_token
6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Pierre Gondois <pierre.gondois(a)arm.com>
[ Upstream commit 8844c3df001bc1d8397fddea341308da63855d53 ]
Make init_of_cache_level() return an error code when the cache
information parsing fails to help detecting missing information.
init_of_cache_level() is only called for riscv. Returning an error
code instead of 0 will prevent detect_cache_attributes() to allocate
memory if an incomplete DT is parsed.
Signed-off-by: Pierre Gondois <pierre.gondois(a)arm.com>
Acked-by: Palmer Dabbelt <palmer(a)rivosinc.com>
Link: https://lore.kernel.org/r/20230104183033.755668-3-pierre.gondois@arm.com
Signed-off-by: Sudeep Holla <sudeep.holla(a)arm.com>
Signed-off-by: Wen Yang <wen.yang(a)linux.dev>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/base/cacheinfo.c | 10 +++++++---
1 file changed, 7 insertions(+), 3 deletions(-)
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -245,11 +245,11 @@ int init_of_cache_level(unsigned int cpu
of_node_put(prev);
prev = np;
if (!of_device_is_compatible(np, "cache"))
- break;
+ goto err_out;
if (of_property_read_u32(np, "cache-level", &level))
- break;
+ goto err_out;
if (level <= levels)
- break;
+ goto err_out;
if (of_property_read_bool(np, "cache-size"))
++leaves;
if (of_property_read_bool(np, "i-cache-size"))
@@ -264,6 +264,10 @@ int init_of_cache_level(unsigned int cpu
this_cpu_ci->num_leaves = leaves;
return 0;
+
+err_out:
+ of_node_put(np);
+ return -EINVAL;
}
#else
6.1-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hugo Villeneuve <hvilleneuve(a)dimonoff.com>
[ Upstream commit 0c84bea0cabc4e2b98a3de88eeb4ff798931f056 ]
Move common code for EFR lock/unlock of mutex into functions for code reuse
and clarity.
With the addition of old_lcr, move irda_mode within struct sc16is7xx_one to
reduce memory usage:
Before: /* size: 752, cachelines: 12, members: 10 */
After: /* size: 744, cachelines: 12, members: 10 */
Signed-off-by: Hugo Villeneuve <hvilleneuve(a)dimonoff.com>
Link: https://lore.kernel.org/r/20231221231823.2327894-17-hugo@hugovil.com
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Stable-dep-of: 1c05bf6c0262 ("serial: sc16is7xx: remove useless enable of enhanced features")
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
drivers/tty/serial/sc16is7xx.c | 106 ++++++++++++++++++++++-------------------
1 file changed, 57 insertions(+), 49 deletions(-)
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -329,8 +329,9 @@ struct sc16is7xx_one {
struct kthread_work reg_work;
struct kthread_delayed_work ms_work;
struct sc16is7xx_one_config config;
- bool irda_mode;
unsigned int old_mctrl;
+ u8 old_lcr; /* Value before EFR access. */
+ bool irda_mode;
};
struct sc16is7xx_port {
@@ -412,6 +413,49 @@ static void sc16is7xx_power(struct uart_
on ? 0 : SC16IS7XX_IER_SLEEP_BIT);
}
+/*
+ * In an amazing feat of design, the Enhanced Features Register (EFR)
+ * shares the address of the Interrupt Identification Register (IIR).
+ * Access to EFR is switched on by writing a magic value (0xbf) to the
+ * Line Control Register (LCR). Any interrupt firing during this time will
+ * see the EFR where it expects the IIR to be, leading to
+ * "Unexpected interrupt" messages.
+ *
+ * Prevent this possibility by claiming a mutex while accessing the EFR,
+ * and claiming the same mutex from within the interrupt handler. This is
+ * similar to disabling the interrupt, but that doesn't work because the
+ * bulk of the interrupt processing is run as a workqueue job in thread
+ * context.
+ */
+static void sc16is7xx_efr_lock(struct uart_port *port)
+{
+ struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+
+ mutex_lock(&one->efr_lock);
+
+ /* Backup content of LCR. */
+ one->old_lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG);
+
+ /* Enable access to Enhanced register set */
+ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_CONF_MODE_B);
+
+ /* Disable cache updates when writing to EFR registers */
+ regcache_cache_bypass(one->regmap, true);
+}
+
+static void sc16is7xx_efr_unlock(struct uart_port *port)
+{
+ struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+
+ /* Re-enable cache updates when writing to normal registers */
+ regcache_cache_bypass(one->regmap, false);
+
+ /* Restore original content of LCR */
+ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, one->old_lcr);
+
+ mutex_unlock(&one->efr_lock);
+}
+
static void sc16is7xx_ier_clear(struct uart_port *port, u8 bit)
{
struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
@@ -538,39 +582,12 @@ static int sc16is7xx_set_baud(struct uar
div /= prescaler;
}
- /* In an amazing feat of design, the Enhanced Features Register shares
- * the address of the Interrupt Identification Register, and is
- * switched in by writing a magic value (0xbf) to the Line Control
- * Register. Any interrupt firing during this time will see the EFR
- * where it expects the IIR to be, leading to "Unexpected interrupt"
- * messages.
- *
- * Prevent this possibility by claiming a mutex while accessing the
- * EFR, and claiming the same mutex from within the interrupt handler.
- * This is similar to disabling the interrupt, but that doesn't work
- * because the bulk of the interrupt processing is run as a workqueue
- * job in thread context.
- */
- mutex_lock(&one->efr_lock);
-
- lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG);
-
- /* Open the LCR divisors for configuration */
- sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
- SC16IS7XX_LCR_CONF_MODE_B);
-
/* Enable enhanced features */
- regcache_cache_bypass(one->regmap, true);
+ sc16is7xx_efr_lock(port);
sc16is7xx_port_update(port, SC16IS7XX_EFR_REG,
SC16IS7XX_EFR_ENABLE_BIT,
SC16IS7XX_EFR_ENABLE_BIT);
-
- regcache_cache_bypass(one->regmap, false);
-
- /* Put LCR back to the normal mode */
- sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
-
- mutex_unlock(&one->efr_lock);
+ sc16is7xx_efr_unlock(port);
/* If bit MCR_CLKSEL is set, the divide by 4 prescaler is activated. */
sc16is7xx_port_update(port, SC16IS7XX_MCR_REG,
@@ -580,7 +597,8 @@ static int sc16is7xx_set_baud(struct uar
mutex_lock(&one->efr_lock);
- /* Open the LCR divisors for configuration */
+ /* Backup LCR and access special register set (DLL/DLH) */
+ lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG);
sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
SC16IS7XX_LCR_CONF_MODE_A);
@@ -590,7 +608,7 @@ static int sc16is7xx_set_baud(struct uar
sc16is7xx_port_write(port, SC16IS7XX_DLL_REG, div % 256);
regcache_cache_bypass(one->regmap, false);
- /* Put LCR back to the normal mode */
+ /* Restore LCR and access to general register set */
sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
mutex_unlock(&one->efr_lock);
@@ -1073,17 +1091,7 @@ static void sc16is7xx_set_termios(struct
if (!(termios->c_cflag & CREAD))
port->ignore_status_mask |= SC16IS7XX_LSR_BRK_ERROR_MASK;
- /* As above, claim the mutex while accessing the EFR. */
- mutex_lock(&one->efr_lock);
-
- sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
- SC16IS7XX_LCR_CONF_MODE_B);
-
/* Configure flow control */
- regcache_cache_bypass(one->regmap, true);
- sc16is7xx_port_write(port, SC16IS7XX_XON1_REG, termios->c_cc[VSTART]);
- sc16is7xx_port_write(port, SC16IS7XX_XOFF1_REG, termios->c_cc[VSTOP]);
-
port->status &= ~(UPSTAT_AUTOCTS | UPSTAT_AUTORTS);
if (termios->c_cflag & CRTSCTS) {
flow |= SC16IS7XX_EFR_AUTOCTS_BIT |
@@ -1095,16 +1103,16 @@ static void sc16is7xx_set_termios(struct
if (termios->c_iflag & IXOFF)
flow |= SC16IS7XX_EFR_SWFLOW1_BIT;
- sc16is7xx_port_update(port,
- SC16IS7XX_EFR_REG,
- SC16IS7XX_EFR_FLOWCTRL_BITS,
- flow);
- regcache_cache_bypass(one->regmap, false);
-
/* Update LCR register */
sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
- mutex_unlock(&one->efr_lock);
+ /* Update EFR registers */
+ sc16is7xx_efr_lock(port);
+ sc16is7xx_port_write(port, SC16IS7XX_XON1_REG, termios->c_cc[VSTART]);
+ sc16is7xx_port_write(port, SC16IS7XX_XOFF1_REG, termios->c_cc[VSTOP]);
+ sc16is7xx_port_update(port, SC16IS7XX_EFR_REG,
+ SC16IS7XX_EFR_FLOWCTRL_BITS, flow);
+ sc16is7xx_efr_unlock(port);
/* Get baud rate generator configuration */
baud = uart_get_baud_rate(port, termios, old,