* [PATCH 7/9] macintosh/via-macii: Use unsigned type for autopoll_devs variable
From: Finn Thain @ 2020-06-28 4:23 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: Laurent Vivier, Mark Cave-Ayland, linux-kernel, linux-m68k,
Geert Uytterhoeven, linuxppc-dev, Joshua Thompson
In-Reply-To: <cover.1593318192.git.fthain@telegraphics.com.au>
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
---
drivers/macintosh/via-macii.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
index e143ddb81de34..447273967e1e8 100644
--- a/drivers/macintosh/via-macii.c
+++ b/drivers/macintosh/via-macii.c
@@ -125,7 +125,7 @@ static bool srq_asserted; /* have to poll for the device that asserted it */
static u8 last_cmd; /* the most recent command byte transmitted */
static u8 last_talk_cmd; /* the most recent Talk command byte transmitted */
static u8 last_poll_cmd; /* the most recent Talk R0 command byte transmitted */
-static int autopoll_devs; /* bits set are device addresses to be polled */
+static unsigned int autopoll_devs; /* bits set are device addresses to poll */
/* Check for MacII style ADB */
static int macii_probe(void)
@@ -291,7 +291,7 @@ static int macii_autopoll(int devs)
local_irq_save(flags);
/* bit 1 == device 1, and so on. */
- autopoll_devs = devs & 0xFFFE;
+ autopoll_devs = (unsigned int)devs & 0xFFFE;
if (!current_req) {
macii_queue_poll();
--
2.26.2
^ permalink raw reply related
* [PATCH 6/9] macintosh/via-macii: Use bool type for reading_reply variable
From: Finn Thain @ 2020-06-28 4:23 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: Laurent Vivier, Mark Cave-Ayland, linux-kernel, linux-m68k,
Geert Uytterhoeven, linuxppc-dev, Joshua Thompson
In-Reply-To: <cover.1593318192.git.fthain@telegraphics.com.au>
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
---
drivers/macintosh/via-macii.c | 10 +++++-----
1 file changed, 5 insertions(+), 5 deletions(-)
diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
index 8d5ef77b4a435..e143ddb81de34 100644
--- a/drivers/macintosh/via-macii.c
+++ b/drivers/macintosh/via-macii.c
@@ -116,7 +116,7 @@ static struct adb_request *current_req; /* first request struct in the queue */
static struct adb_request *last_req; /* last request struct in the queue */
static unsigned char reply_buf[16]; /* storage for autopolled replies */
static unsigned char *reply_ptr; /* next byte in reply_buf or req->reply */
-static int reading_reply; /* store reply in reply_buf else req->reply */
+static bool reading_reply; /* store reply in reply_buf else req->reply */
static int data_index; /* index of the next byte to send from req->data */
static int reply_len; /* number of bytes received in reply_buf or req->reply */
static int status; /* VIA's ADB status bits captured upon interrupt */
@@ -394,7 +394,7 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
WARN_ON((status & ST_MASK) != ST_IDLE);
reply_ptr = reply_buf;
- reading_reply = 0;
+ reading_reply = false;
bus_timeout = false;
srq_asserted = false;
@@ -442,7 +442,7 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
*/
macii_state = reading;
- reading_reply = 0;
+ reading_reply = false;
reply_ptr = reply_buf;
*reply_ptr = last_talk_cmd;
reply_len = 1;
@@ -456,7 +456,7 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
if (req->reply_expected) {
macii_state = reading;
- reading_reply = 1;
+ reading_reply = true;
reply_ptr = req->reply;
*reply_ptr = req->data[1];
reply_len = 1;
@@ -466,7 +466,7 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
} else if ((req->data[1] & OP_MASK) == TALK) {
macii_state = reading;
- reading_reply = 0;
+ reading_reply = false;
reply_ptr = reply_buf;
*reply_ptr = req->data[1];
reply_len = 1;
--
2.26.2
^ permalink raw reply related
* [PATCH 5/9] macintosh/via-macii: Handle poll replies correctly
From: Finn Thain @ 2020-06-28 4:23 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: Laurent Vivier, Mark Cave-Ayland, linux-kernel, linux-m68k,
Geert Uytterhoeven, linuxppc-dev, Joshua Thompson
In-Reply-To: <cover.1593318192.git.fthain@telegraphics.com.au>
Userspace applications may use /dev/adb to send Talk requests. Such
requests always have req->reply_expected == 1. The same is true of Talk
requests sent by the kernel, except for poll requests queued internally
by the via-macii driver. Those requests have req->reply_expected == 0.
Consequently, poll reply packets get treated like autopoll reply packets.
(It doesn't make sense to try to distinguish them.) Always enter 'reading'
state after a poll request, so that the reply gets collected and passed
to adb_input(), and none go missing.
All Talk replies passed to adb_input() come from polling or autopolling,
so call adb_input() with the autopoll parameter set to 1.
Fixes: d95fd5fce88f0 ("m68k: Mac II ADB fixes") # v5.0+
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
---
drivers/macintosh/via-macii.c | 20 ++++++++++++++++++--
1 file changed, 18 insertions(+), 2 deletions(-)
diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
index d29c87943ca46..8d5ef77b4a435 100644
--- a/drivers/macintosh/via-macii.c
+++ b/drivers/macintosh/via-macii.c
@@ -463,6 +463,21 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
via[ACR] &= ~SR_OUT;
x = via[SR];
+ } else if ((req->data[1] & OP_MASK) == TALK) {
+ macii_state = reading;
+
+ reading_reply = 0;
+ reply_ptr = reply_buf;
+ *reply_ptr = req->data[1];
+ reply_len = 1;
+
+ via[ACR] &= ~SR_OUT;
+ x = via[SR];
+
+ req->complete = 1;
+ current_req = req->next;
+ if (req->done)
+ (*req->done)(req);
} else {
macii_state = idle;
@@ -510,8 +525,9 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
current_req = req->next;
if (req->done)
(*req->done)(req);
- } else if (reply_len && autopoll_devs) {
- adb_input(reply_buf, reply_len, 0);
+ } else if (reply_len && autopoll_devs &&
+ reply_buf[0] == last_poll_cmd) {
+ adb_input(reply_buf, reply_len, 1);
}
break;
}
--
2.26.2
^ permalink raw reply related
* [PATCH 3/9] macintosh/via-macii: Handle /CTLR_IRQ signal correctly
From: Finn Thain @ 2020-06-28 4:23 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: Laurent Vivier, Mark Cave-Ayland, linux-kernel, linux-m68k,
Geert Uytterhoeven, linuxppc-dev, Joshua Thompson
In-Reply-To: <cover.1593318192.git.fthain@telegraphics.com.au>
I'm told that the /CTLR_IRQ signal from the ADB transceiver gets
interpreted by MacOS to mean SRQ, bus timeout or end-of-packet depending
on the circumstances, and that Linux's via-macii driver does not
correctly interpret this signal.
Instead, the via-macii driver interprets certain received byte values
(0x00 and 0xFF) as signalling end of packet and bus timeout
(respectively). Problem is, those values can also appear under other
circumstances.
This patch changes the bus timeout, end of packet and SRQ detection logic
to bring it closer to the logic that MacOS reportedly uses.
Fixes: 1da177e4c3f41 ("Linux-2.6.12-rc2") # v5.0+
Reported-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
---
drivers/macintosh/via-macii.c | 166 ++++++++++++++++++++--------------
1 file changed, 97 insertions(+), 69 deletions(-)
diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
index d4f1a65c5f1fd..6a5cd7de05baf 100644
--- a/drivers/macintosh/via-macii.c
+++ b/drivers/macintosh/via-macii.c
@@ -80,6 +80,8 @@ static volatile unsigned char *via;
/* ADB command byte structure */
#define ADDR_MASK 0xF0
#define CMD_MASK 0x0F
+#define OP_MASK 0x0C
+#define TALK 0x0C
static int macii_init_via(void);
static void macii_start(void);
@@ -119,9 +121,10 @@ static int reading_reply; /* store reply in reply_buf else req->reply */
static int data_index; /* index of the next byte to send from req->data */
static int reply_len; /* number of bytes received in reply_buf or req->reply */
static int status; /* VIA's ADB status bits captured upon interrupt */
-static int last_status; /* status bits as at previous interrupt */
-static int srq_asserted; /* have to poll for the device that asserted it */
+static bool bus_timeout; /* no data was sent by the device */
+static bool srq_asserted; /* have to poll for the device that asserted it */
static u8 last_cmd; /* the most recent command byte transmitted */
+static u8 last_talk_cmd; /* the most recent Talk command byte transmitted */
static u8 last_poll_cmd; /* the most recent Talk R0 command byte transmitted */
static int autopoll_devs; /* bits set are device addresses to be polled */
@@ -170,7 +173,6 @@ static int macii_init_via(void)
/* Set up state: idle */
via[B] |= ST_IDLE;
- last_status = via[B] & (ST_MASK | CTLR_IRQ);
/* Shift register on input */
via[ACR] = (via[ACR] & ~SR_CTRL) | SR_EXT;
@@ -336,13 +338,6 @@ static void macii_start(void)
* And req->nbytes is the number of bytes of real data plus one.
*/
- /* store command byte */
- last_cmd = req->data[1];
-
- /* If this is a Talk Register 0 command, store the command byte */
- if ((last_cmd & CMD_MASK) == ADB_READREG(0, 0))
- last_poll_cmd = last_cmd;
-
/* Output mode */
via[ACR] |= SR_OUT;
/* Load data */
@@ -352,6 +347,9 @@ static void macii_start(void)
macii_state = sending;
data_index = 2;
+
+ bus_timeout = false;
+ srq_asserted = false;
}
/*
@@ -360,15 +358,17 @@ static void macii_start(void)
* generating shift register interrupts (SR_INT) for us. This means there has
* to be activity on the ADB bus. The chip will poll to achieve this.
*
- * The basic ADB state machine was left unchanged from the original MacII code
- * by Alan Cox, which was based on the CUDA driver for PowerMac.
- * The syntax of the ADB status lines is totally different on MacII,
- * though. MacII uses the states Command -> Even -> Odd -> Even ->...-> Idle
- * for sending and Idle -> Even -> Odd -> Even ->...-> Idle for receiving.
- * Start and end of a receive packet are signalled by asserting /IRQ on the
- * interrupt line (/IRQ means the CTLR_IRQ bit in port B; not to be confused
- * with the VIA shift register interrupt. /IRQ never actually interrupts the
- * processor, it's just an ordinary input.)
+ * The VIA Port B output signalling works as follows. After the ADB transceiver
+ * sees a transition on the PB4 and PB5 lines it will crank over the VIA shift
+ * register which eventually raises the SR_INT interrupt. The PB4/PB5 outputs
+ * are toggled with each byte as the ADB transaction progresses.
+ *
+ * Request with no reply expected (and empty transceiver buffer):
+ * CMD -> IDLE
+ * Request with expected reply packet (or with buffered autopoll packet):
+ * CMD -> EVEN -> ODD -> EVEN -> ... -> IDLE
+ * Unsolicited packet:
+ * IDLE -> EVEN -> ODD -> EVEN -> ... -> IDLE
*/
static irqreturn_t macii_interrupt(int irq, void *arg)
{
@@ -388,31 +388,31 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
}
}
- last_status = status;
status = via[B] & (ST_MASK | CTLR_IRQ);
switch (macii_state) {
case idle:
- if (reading_reply) {
- reply_ptr = current_req->reply;
- } else {
- WARN_ON(current_req);
- reply_ptr = reply_buf;
- }
+ WARN_ON((status & ST_MASK) != ST_IDLE);
+
+ reply_ptr = reply_buf;
+ reading_reply = 0;
+
+ bus_timeout = false;
+ srq_asserted = false;
x = via[SR];
- if ((status & CTLR_IRQ) && (x == 0xFF)) {
- /* Bus timeout without SRQ sequence:
- * data is "FF" while CTLR_IRQ is "H"
+ if (!(status & CTLR_IRQ)) {
+ /* /CTLR_IRQ asserted in idle state means we must
+ * read an autopoll reply from the transceiver buffer.
*/
- reply_len = 0;
- srq_asserted = 0;
- macii_state = read_done;
- } else {
macii_state = reading;
*reply_ptr = x;
reply_len = 1;
+ } else {
+ /* bus timeout */
+ macii_state = read_done;
+ reply_len = 0;
}
/* set ADB state = even for first data byte */
@@ -421,13 +421,52 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
case sending:
req = current_req;
- if (data_index >= req->nbytes) {
+
+ if (status == (ST_CMD | CTLR_IRQ)) {
+ /* /CTLR_IRQ de-asserted after the command byte means
+ * the host can continue with the transaction.
+ */
+
+ /* Store command byte */
+ last_cmd = req->data[1];
+ if ((last_cmd & OP_MASK) == TALK) {
+ last_talk_cmd = last_cmd;
+ if ((last_cmd & CMD_MASK) == ADB_READREG(0, 0))
+ last_poll_cmd = last_cmd;
+ }
+ }
+
+ if (status == ST_CMD) {
+ /* /CTLR_IRQ asserted after the command byte means we
+ * must read an autopoll reply. The first byte was
+ * lost because the shift register was an output.
+ */
+ macii_state = reading;
+
+ reading_reply = 0;
+ reply_ptr = reply_buf;
+ *reply_ptr = last_talk_cmd;
+ reply_len = 1;
+
+ /* reset to shift in */
+ via[ACR] &= ~SR_OUT;
+ x = via[SR];
+ } else if (data_index >= req->nbytes) {
req->sent = 1;
- macii_state = idle;
if (req->reply_expected) {
+ macii_state = reading;
+
reading_reply = 1;
+ reply_ptr = req->reply;
+ *reply_ptr = req->data[1];
+ reply_len = 1;
+
+ via[ACR] &= ~SR_OUT;
+ x = via[SR];
} else {
+ macii_state = idle;
+
req->complete = 1;
current_req = req->next;
if (req->done)
@@ -438,25 +477,26 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
if (current_req && macii_state == idle)
macii_start();
- }
- if (macii_state == idle) {
- /* reset to shift in */
- via[ACR] &= ~SR_OUT;
- x = via[SR];
- /* set ADB state idle - might get SRQ */
- via[B] = (via[B] & ~ST_MASK) | ST_IDLE;
+ if (macii_state == idle) {
+ /* reset to shift in */
+ via[ACR] &= ~SR_OUT;
+ x = via[SR];
+ /* set ADB state idle - might get SRQ */
+ via[B] = (via[B] & ~ST_MASK) | ST_IDLE;
+ }
+ break;
}
} else {
via[SR] = req->data[data_index++];
+ }
- if ((via[B] & ST_MASK) == ST_CMD) {
- /* just sent the command byte, set to EVEN */
- via[B] = (via[B] & ~ST_MASK) | ST_EVEN;
- } else {
- /* invert state bits, toggle ODD/EVEN */
- via[B] ^= ST_MASK;
- }
+ if ((via[B] & ST_MASK) == ST_CMD) {
+ /* just sent the command byte, set to EVEN */
+ via[B] = (via[B] & ~ST_MASK) | ST_EVEN;
+ } else {
+ /* invert state bits, toggle ODD/EVEN */
+ via[B] ^= ST_MASK;
}
break;
@@ -465,28 +505,13 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
WARN_ON((status & ST_MASK) == ST_CMD ||
(status & ST_MASK) == ST_IDLE);
- /* Bus timeout with SRQ sequence:
- * data is "XX FF" while CTLR_IRQ is "L L"
- * End of packet without SRQ sequence:
- * data is "XX...YY 00" while CTLR_IRQ is "L...H L"
- * End of packet SRQ sequence:
- * data is "XX...YY 00" while CTLR_IRQ is "L...L L"
- * (where XX is the first response byte and
- * YY is the last byte of valid response data.)
- */
-
- srq_asserted = 0;
if (!(status & CTLR_IRQ)) {
- if (x == 0xFF) {
- if (!(last_status & CTLR_IRQ)) {
- macii_state = read_done;
- reply_len = 0;
- srq_asserted = 1;
- }
- } else if (x == 0x00) {
+ if (status == ST_EVEN && reply_len == 1) {
+ bus_timeout = true;
+ } else if (status == ST_ODD && reply_len == 2) {
+ srq_asserted = true;
+ } else {
macii_state = read_done;
- if (!(last_status & CTLR_IRQ))
- srq_asserted = 1;
}
}
@@ -504,6 +529,9 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
case read_done:
x = via[SR];
+ if (bus_timeout)
+ reply_len = 0;
+
if (reading_reply) {
reading_reply = 0;
req = current_req;
--
2.26.2
^ permalink raw reply related
* [PATCH 2/9] macintosh/via-macii: Poll the device most likely to respond
From: Finn Thain @ 2020-06-28 4:23 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: Laurent Vivier, Mark Cave-Ayland, linux-kernel, linux-m68k,
Geert Uytterhoeven, linuxppc-dev, Joshua Thompson
In-Reply-To: <cover.1593318192.git.fthain@telegraphics.com.au>
Poll the most recently polled device by default, rather than the lowest
device address that happens to be enabled in autopoll_devs. This improves
input latency. Re-use macii_queue_poll() rather than duplicate that logic.
This eliminates a static struct and function.
Fixes: d95fd5fce88f0 ("m68k: Mac II ADB fixes") # v5.0+
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
---
drivers/macintosh/via-macii.c | 99 +++++++++++++++++++----------------
1 file changed, 53 insertions(+), 46 deletions(-)
diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
index 6aa903529570d..d4f1a65c5f1fd 100644
--- a/drivers/macintosh/via-macii.c
+++ b/drivers/macintosh/via-macii.c
@@ -77,6 +77,10 @@ static volatile unsigned char *via;
#define ST_ODD 0x20 /* ADB state: odd data byte */
#define ST_IDLE 0x30 /* ADB state: idle, nothing to send */
+/* ADB command byte structure */
+#define ADDR_MASK 0xF0
+#define CMD_MASK 0x0F
+
static int macii_init_via(void);
static void macii_start(void);
static irqreturn_t macii_interrupt(int irq, void *arg);
@@ -117,7 +121,8 @@ static int reply_len; /* number of bytes received in reply_buf or req->reply */
static int status; /* VIA's ADB status bits captured upon interrupt */
static int last_status; /* status bits as at previous interrupt */
static int srq_asserted; /* have to poll for the device that asserted it */
-static int command_byte; /* the most recent command byte transmitted */
+static u8 last_cmd; /* the most recent command byte transmitted */
+static u8 last_poll_cmd; /* the most recent Talk R0 command byte transmitted */
static int autopoll_devs; /* bits set are device addresses to be polled */
/* Check for MacII style ADB */
@@ -179,35 +184,49 @@ static int macii_init_via(void)
/* Send an ADB poll (Talk Register 0 command prepended to the request queue) */
static void macii_queue_poll(void)
{
- /* No point polling the active device as it will never assert SRQ, so
- * poll the next device in the autopoll list. This could leave us
- * stuck in a polling loop if an unprobed device is asserting SRQ.
- * In theory, that could only happen if a device was plugged in after
- * probing started. Unplugging it again will break the cycle.
- * (Simply polling the next higher device often ends up polling almost
- * every device (after wrapping around), which takes too long.)
- */
- int device_mask;
- int next_device;
static struct adb_request req;
+ unsigned char poll_command;
+ unsigned int poll_addr;
+ /* This only polls devices in the autopoll list, which assumes that
+ * unprobed devices never assert SRQ. That could happen if a device was
+ * plugged in after the adb bus scan. Unplugging it again will resolve
+ * the problem. This behaviour is similar to MacOS.
+ */
if (!autopoll_devs)
return;
- device_mask = (1 << (((command_byte & 0xF0) >> 4) + 1)) - 1;
- if (autopoll_devs & ~device_mask)
- next_device = ffs(autopoll_devs & ~device_mask) - 1;
- else
- next_device = ffs(autopoll_devs) - 1;
+ /* The device most recently polled may not be the best device to poll
+ * right now. Some other device(s) may have signalled SRQ (the active
+ * device won't do that). Or the autopoll list may have been changed.
+ * Try polling the next higher address.
+ */
+ poll_addr = (last_poll_cmd & ADDR_MASK) >> 4;
+ if ((srq_asserted && last_cmd == last_poll_cmd) ||
+ !(autopoll_devs & (1 << poll_addr))) {
+ unsigned int higher_devs;
+
+ higher_devs = autopoll_devs & -(1 << (poll_addr + 1));
+ poll_addr = ffs(higher_devs ? higher_devs : autopoll_devs) - 1;
+ }
- adb_request(&req, NULL, ADBREQ_NOSEND, 1, ADB_READREG(next_device, 0));
+ /* Send a Talk Register 0 command */
+ poll_command = ADB_READREG(poll_addr, 0);
+
+ /* No need to repeat this Talk command. The transceiver will do that
+ * as long as it is idle.
+ */
+ if (poll_command == last_cmd)
+ return;
+
+ adb_request(&req, NULL, ADBREQ_NOSEND, 1, poll_command);
req.sent = 0;
req.complete = 0;
req.reply_len = 0;
req.next = current_req;
- if (current_req != NULL) {
+ if (WARN_ON(current_req)) {
current_req = &req;
} else {
current_req = &req;
@@ -266,37 +285,22 @@ static int macii_write(struct adb_request *req)
/* Start auto-polling */
static int macii_autopoll(int devs)
{
- static struct adb_request req;
unsigned long flags;
- int err = 0;
local_irq_save(flags);
/* bit 1 == device 1, and so on. */
autopoll_devs = devs & 0xFFFE;
- if (autopoll_devs && !current_req) {
- /* Send a Talk Reg 0. The controller will repeatedly transmit
- * this as long as it is idle.
- */
- adb_request(&req, NULL, ADBREQ_NOSEND, 1,
- ADB_READREG(ffs(autopoll_devs) - 1, 0));
- err = macii_write(&req);
+ if (!current_req) {
+ macii_queue_poll();
+ if (current_req && macii_state == idle)
+ macii_start();
}
local_irq_restore(flags);
- return err;
-}
-static inline int need_autopoll(void)
-{
- /* Was the last command Talk Reg 0
- * and is the target on the autopoll list?
- */
- if ((command_byte & 0x0F) == 0x0C &&
- ((1 << ((command_byte & 0xF0) >> 4)) & autopoll_devs))
- return 0;
- return 1;
+ return 0;
}
/* Prod the chip without interrupts */
@@ -333,7 +337,12 @@ static void macii_start(void)
*/
/* store command byte */
- command_byte = req->data[1];
+ last_cmd = req->data[1];
+
+ /* If this is a Talk Register 0 command, store the command byte */
+ if ((last_cmd & CMD_MASK) == ADB_READREG(0, 0))
+ last_poll_cmd = last_cmd;
+
/* Output mode */
via[ACR] |= SR_OUT;
/* Load data */
@@ -424,10 +433,11 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
if (req->done)
(*req->done)(req);
- if (current_req)
+ if (!current_req)
+ macii_queue_poll();
+
+ if (current_req && macii_state == idle)
macii_start();
- else if (need_autopoll())
- macii_autopoll(autopoll_devs);
}
if (macii_state == idle) {
@@ -507,14 +517,11 @@ static irqreturn_t macii_interrupt(int irq, void *arg)
macii_state = idle;
- /* SRQ seen before, initiate poll now */
- if (srq_asserted)
+ if (!current_req)
macii_queue_poll();
if (current_req)
macii_start();
- else if (need_autopoll())
- macii_autopoll(autopoll_devs);
if (macii_state == idle)
via[B] = (via[B] & ~ST_MASK) | ST_IDLE;
--
2.26.2
^ permalink raw reply related
* [PATCH 1/9] macintosh/via-macii: Access autopoll_devs when inside lock
From: Finn Thain @ 2020-06-28 4:23 UTC (permalink / raw)
To: Benjamin Herrenschmidt
Cc: Laurent Vivier, Mark Cave-Ayland, linux-kernel, linux-m68k,
Geert Uytterhoeven, linuxppc-dev, Joshua Thompson
In-Reply-To: <cover.1593318192.git.fthain@telegraphics.com.au>
The interrupt handler should be excluded when accessing the autopoll_devs
variable.
Fixes: d95fd5fce88f0 ("m68k: Mac II ADB fixes") # v5.0+
Tested-by: Stan Johnson <userm57@yahoo.com>
Signed-off-by: Finn Thain <fthain@telegraphics.com.au>
---
drivers/macintosh/via-macii.c | 9 +++------
1 file changed, 3 insertions(+), 6 deletions(-)
diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
index ac824d7b2dcfc..6aa903529570d 100644
--- a/drivers/macintosh/via-macii.c
+++ b/drivers/macintosh/via-macii.c
@@ -270,15 +270,12 @@ static int macii_autopoll(int devs)
unsigned long flags;
int err = 0;
+ local_irq_save(flags);
+
/* bit 1 == device 1, and so on. */
autopoll_devs = devs & 0xFFFE;
- if (!autopoll_devs)
- return 0;
-
- local_irq_save(flags);
-
- if (current_req == NULL) {
+ if (autopoll_devs && !current_req) {
/* Send a Talk Reg 0. The controller will repeatedly transmit
* this as long as it is idle.
*/
--
2.26.2
^ permalink raw reply related
* Re: [PATCH 01/11] kexec_file: allow archs to handle special regions while locating memory hole
From: piliu @ 2020-06-28 2:28 UTC (permalink / raw)
To: Hari Bathini, Michael Ellerman, Andrew Morton
Cc: Kexec-ml, Petr Tesarik, Mahesh J Salgaonkar, Sourabh Jain, lkml,
linuxppc-dev, Mimi Zohar, Thiago Jung Bauermann, Dave Young,
Vivek Goyal, Eric Biederman
In-Reply-To: <159319828304.16351.6990340111766605842.stgit@hbathini.in.ibm.com>
Hi Hari,
If in [4/11], get_exclude_memory_ranges() turns out to be unnecessary
,then this patch is abundant either. As my understanding, memblock has
already helped to achieved the purpose that get_exclude_memory_ranges()
wants.
Thanks,
Pingfan
On 06/27/2020 03:04 AM, Hari Bathini wrote:
> Some archs can have special memory regions, within the given memory
> range, which can't be used for the buffer in a kexec segment. As
> kexec_add_buffer() function is being called from generic code as well,
> add weak arch_kexec_add_buffer definition for archs to override & take
> care of special regions before trying to locate a memory hole.
>
> Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
> ---
> include/linux/kexec.h | 5 +++++
> kernel/kexec_file.c | 37 +++++++++++++++++++++++++++++++++----
> 2 files changed, 38 insertions(+), 4 deletions(-)
>
> diff --git a/include/linux/kexec.h b/include/linux/kexec.h
> index 1776eb2..1237682 100644
> --- a/include/linux/kexec.h
> +++ b/include/linux/kexec.h
> @@ -195,6 +195,11 @@ int __weak arch_kexec_apply_relocations(struct purgatory_info *pi,
> const Elf_Shdr *relsec,
> const Elf_Shdr *symtab);
>
> +extern int arch_kexec_add_buffer(struct kexec_buf *kbuf);
> +
> +/* arch_kexec_add_buffer calls this when it is ready */
> +extern int __kexec_add_buffer(struct kexec_buf *kbuf);
> +
> extern int kexec_add_buffer(struct kexec_buf *kbuf);
> int kexec_locate_mem_hole(struct kexec_buf *kbuf);
>
> diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
> index bb05fd5..a0b4f7f 100644
> --- a/kernel/kexec_file.c
> +++ b/kernel/kexec_file.c
> @@ -669,10 +669,6 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
> */
> int kexec_add_buffer(struct kexec_buf *kbuf)
> {
> -
> - struct kexec_segment *ksegment;
> - int ret;
> -
> /* Currently adding segment this way is allowed only in file mode */
> if (!kbuf->image->file_mode)
> return -EINVAL;
> @@ -696,6 +692,25 @@ int kexec_add_buffer(struct kexec_buf *kbuf)
> kbuf->memsz = ALIGN(kbuf->memsz, PAGE_SIZE);
> kbuf->buf_align = max(kbuf->buf_align, PAGE_SIZE);
>
> + return arch_kexec_add_buffer(kbuf);
> +}
> +
> +/**
> + * __kexec_add_buffer - arch_kexec_add_buffer would call this function after
> + * updating kbuf, to place a buffer in a kexec segment.
> + * @kbuf: Buffer contents and memory parameters.
> + *
> + * This function assumes that kexec_mutex is held.
> + * On successful return, @kbuf->mem will have the physical address of
> + * the buffer in memory.
> + *
> + * Return: 0 on success, negative errno on error.
> + */
> +int __kexec_add_buffer(struct kexec_buf *kbuf)
> +{
> + struct kexec_segment *ksegment;
> + int ret;
> +
> /* Walk the RAM ranges and allocate a suitable range for the buffer */
> ret = kexec_locate_mem_hole(kbuf);
> if (ret)
> @@ -711,6 +726,20 @@ int kexec_add_buffer(struct kexec_buf *kbuf)
> return 0;
> }
>
> +/**
> + * arch_kexec_add_buffer - Some archs have memory regions within the given
> + * range that can't be used to place a kexec segment.
> + * Such archs can override this function to take care
> + * of them before trying to locate the memory hole.
> + * @kbuf: Buffer contents and memory parameters.
> + *
> + * Return: 0 on success, negative errno on error.
> + */
> +int __weak arch_kexec_add_buffer(struct kexec_buf *kbuf)
> +{
> + return __kexec_add_buffer(kbuf);
> +}
> +
> /* Calculate and store the digest of segments */
> static int kexec_calculate_store_digests(struct kimage *image)
> {
>
>
> _______________________________________________
> kexec mailing list
> kexec@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/kexec
>
^ permalink raw reply
* Re: [PATCH 04/11] ppc64/kexec_file: avoid stomping memory used by special regions
From: piliu @ 2020-06-28 2:14 UTC (permalink / raw)
To: Hari Bathini, Michael Ellerman, Andrew Morton
Cc: Kexec-ml, Petr Tesarik, Mahesh J Salgaonkar, Sourabh Jain, lkml,
linuxppc-dev, Mimi Zohar, Thiago Jung Bauermann, Dave Young,
Vivek Goyal, Eric Biederman
In-Reply-To: <159319831192.16351.17443438699302756548.stgit@hbathini.in.ibm.com>
Hi Hari,
After a quick through for this series, I have a few question/comment on
this patch for the time being. Pls see comment inline.
On 06/27/2020 03:05 AM, Hari Bathini wrote:
> crashkernel region could have an overlap with special memory regions
> like opal, rtas, tce-table & such. These regions are referred to as
> exclude memory ranges. Setup this ranges during image probe in order
> to avoid them while finding the buffer for different kdump segments.
> Implement kexec_locate_mem_hole_ppc64() that locates a memory hole
> accounting for these ranges. Also, override arch_kexec_add_buffer()
> to locate a memory hole & later call __kexec_add_buffer() function
> with kbuf->mem set to skip the generic locate memory hole lookup.
>
> Signed-off-by: Hari Bathini <hbathini@linux.ibm.com>
> ---
> arch/powerpc/include/asm/crashdump-ppc64.h | 10 +
> arch/powerpc/include/asm/kexec.h | 7 -
> arch/powerpc/kexec/elf_64.c | 7 +
> arch/powerpc/kexec/file_load_64.c | 292 ++++++++++++++++++++++++++++
> 4 files changed, 312 insertions(+), 4 deletions(-)
> create mode 100644 arch/powerpc/include/asm/crashdump-ppc64.h
>
> diff --git a/arch/powerpc/include/asm/crashdump-ppc64.h b/arch/powerpc/include/asm/crashdump-ppc64.h
> new file mode 100644
> index 0000000..3596c25
> --- /dev/null
> +++ b/arch/powerpc/include/asm/crashdump-ppc64.h
> @@ -0,0 +1,10 @@
> +/* SPDX-License-Identifier: GPL-2.0-or-later */
> +#ifndef _ARCH_POWERPC_KEXEC_CRASHDUMP_PPC64_H
> +#define _ARCH_POWERPC_KEXEC_CRASHDUMP_PPC64_H
> +
> +/* min & max addresses for kdump load segments */
> +#define KDUMP_BUF_MIN (crashk_res.start)
> +#define KDUMP_BUF_MAX ((crashk_res.end < ppc64_rma_size) ? \
> + crashk_res.end : (ppc64_rma_size - 1))
> +
> +#endif /* __ARCH_POWERPC_KEXEC_CRASHDUMP_PPC64_H */
> diff --git a/arch/powerpc/include/asm/kexec.h b/arch/powerpc/include/asm/kexec.h
> index 7008ea1..bf47a01 100644
> --- a/arch/powerpc/include/asm/kexec.h
> +++ b/arch/powerpc/include/asm/kexec.h
> @@ -100,14 +100,16 @@ void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_co
> #ifdef CONFIG_KEXEC_FILE
> extern const struct kexec_file_ops kexec_elf64_ops;
>
> -#ifdef CONFIG_IMA_KEXEC
> #define ARCH_HAS_KIMAGE_ARCH
>
> struct kimage_arch {
> + struct crash_mem *exclude_ranges;
> +
> +#ifdef CONFIG_IMA_KEXEC
> phys_addr_t ima_buffer_addr;
> size_t ima_buffer_size;
> -};
> #endif
> +};
>
> int setup_purgatory(struct kimage *image, const void *slave_code,
> const void *fdt, unsigned long kernel_load_addr,
> @@ -125,6 +127,7 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
> unsigned long initrd_load_addr,
> unsigned long initrd_len, const char *cmdline);
> #endif /* CONFIG_PPC64 */
> +
> #endif /* CONFIG_KEXEC_FILE */
>
> #else /* !CONFIG_KEXEC_CORE */
> diff --git a/arch/powerpc/kexec/elf_64.c b/arch/powerpc/kexec/elf_64.c
> index 23ad04c..c695f94 100644
> --- a/arch/powerpc/kexec/elf_64.c
> +++ b/arch/powerpc/kexec/elf_64.c
> @@ -22,6 +22,7 @@
> #include <linux/of_fdt.h>
> #include <linux/slab.h>
> #include <linux/types.h>
> +#include <asm/crashdump-ppc64.h>
>
> static void *elf64_load(struct kimage *image, char *kernel_buf,
> unsigned long kernel_len, char *initrd,
> @@ -46,6 +47,12 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
> if (ret)
> goto out;
>
> + if (image->type == KEXEC_TYPE_CRASH) {
> + /* min & max buffer values for kdump case */
> + kbuf.buf_min = pbuf.buf_min = KDUMP_BUF_MIN;
> + kbuf.buf_max = pbuf.buf_max = KDUMP_BUF_MAX;
> + }
> +
> ret = kexec_elf_load(image, &ehdr, &elf_info, &kbuf, &kernel_load_addr);
> if (ret)
> goto out;
> diff --git a/arch/powerpc/kexec/file_load_64.c b/arch/powerpc/kexec/file_load_64.c
> index e6bff960..f1d7160 100644
> --- a/arch/powerpc/kexec/file_load_64.c
> +++ b/arch/powerpc/kexec/file_load_64.c
> @@ -17,6 +17,8 @@
> #include <linux/kexec.h>
> #include <linux/of_fdt.h>
> #include <linux/libfdt.h>
> +#include <asm/kexec_ranges.h>
> +#include <asm/crashdump-ppc64.h>
>
> const struct kexec_file_ops * const kexec_file_loaders[] = {
> &kexec_elf64_ops,
> @@ -24,6 +26,247 @@ const struct kexec_file_ops * const kexec_file_loaders[] = {
> };
>
> /**
> + * get_exclude_memory_ranges - Get exclude memory ranges. This list includes
> + * regions like opal/rtas, tce-table, initrd,
> + * kernel, htab which should be avoided while
> + * setting up kexec load segments.
> + * @mem_ranges: Range list to add the memory ranges to.
> + *
> + * Returns 0 on success, negative errno on error.
> + */
> +static int get_exclude_memory_ranges(struct crash_mem **mem_ranges)
Is it needed? See the comment below.
> +{
> + int ret;
> +
> + ret = add_tce_mem_ranges(mem_ranges);
> + if (ret)
> + goto out;
> +
> + ret = add_initrd_mem_range(mem_ranges);
> + if (ret)
> + goto out;
> +
> + ret = add_htab_mem_range(mem_ranges);
> + if (ret)
> + goto out;
> +
> + ret = add_kernel_mem_range(mem_ranges);
> + if (ret)
> + goto out;
> +
> + ret = add_rtas_mem_range(mem_ranges, false);
> + if (ret)
> + goto out;
> +
> + ret = add_opal_mem_range(mem_ranges, false);
> + if (ret)
> + goto out;
> +
> + ret = add_reserved_ranges(mem_ranges);
> + if (ret)
> + goto out;
> +
> + /* exclude memory ranges should be sorted for easy lookup */
> + sort_memory_ranges(*mem_ranges);
> +out:
> + if (ret)
> + pr_err("Failed to setup exclude memory ranges\n");
> + return ret;
> +}
> +
> +/**
> + * __locate_mem_hole_ppc64 - Tests if the memory hole between buf_min & buf_max
> + * is large enough for the buffer. If true, sets
> + * kbuf->mem to the buffer.
> + * @kbuf: Buffer contents and memory parameters.
> + * @buf_min: Minimum address for the buffer.
> + * @buf_max: Maximum address for the buffer.
> + *
> + * Returns 0 on success, negative errno on error.
> + */
> +static int __locate_mem_hole_ppc64(struct kexec_buf *kbuf,
> + u64 buf_min, u64 buf_max)
> +{
> + int ret = -EADDRNOTAVAIL;
> +
> + buf_min = ALIGN(buf_min, kbuf->buf_align);
> +
> + if (buf_min < buf_max &&
> + (buf_max - buf_min + 1) >= kbuf->memsz) {
> + /*
> + * Suitable memory range found. Set kbuf->mem here to skip
> + * locate memory hole routine in __kexec_add_buffer() call.
> + */
> + ret = 0;
> + if (kbuf->top_down)
> + kbuf->mem = ALIGN_DOWN(buf_max - kbuf->memsz + 1,
> + kbuf->buf_align);
> + else
> + kbuf->mem = buf_min;
> + }
> +
> + return ret;
> +}
> +
> +/**
> + * locate_mem_hole_top_down_ppc64 - Skip special memory regions to find a
> + * suitable buffer with top down approach.
> + * @kbuf: Buffer contents and memory parameters.
> + * @buf_min: Minimum address for the buffer.
> + * @buf_max: Maximum address for the buffer.
> + * @emem: Exclude memory ranges.
> + *
> + * Returns 0 on success, negative errno on error.
> + */
> +static int locate_mem_hole_top_down_ppc64(struct kexec_buf *kbuf,
> + u64 buf_min, u64 buf_max,
> + const struct crash_mem *emem)
> +{
> + int i, ret = 0, err = -EADDRNOTAVAIL;
> + u64 start, end, tmin, tmax;
> +
> + tmax = buf_max;
> + for (i = (emem->nr_ranges - 1); i >= 0; i--) {
> + start = emem->ranges[i].start;
> + end = emem->ranges[i].end;
> +
> + if (start > tmax)
> + continue;
> +
> + if (end < tmax) {
> + tmin = (end < buf_min ? buf_min : end + 1);
> + ret = __locate_mem_hole_ppc64(kbuf, tmin, tmax);
> + if (!ret)
> + return 0;
> + }
> +
> + tmax = start - 1;
> +
> + if (tmax < buf_min) {
> + ret = err;
> + break;
> + }
> + ret = 0;
> + }
> +
> + if (!ret) {
> + tmin = buf_min;
> + ret = __locate_mem_hole_ppc64(kbuf, tmin, tmax);
> + }
> + return ret;
> +}
> +
> +/**
> + * locate_mem_hole_bottom_up_ppc64 - Skip special memory regions to find a
> + * suitable buffer with bottom up approach.
> + * @kbuf: Buffer contents and memory parameters.
> + * @buf_min: Minimum address for the buffer.
> + * @buf_max: Maximum address for the buffer.
> + * @emem: Exclude memory ranges.
> + *
> + * Returns 0 on success, negative errno on error.
> + */
> +static int locate_mem_hole_bottom_up_ppc64(struct kexec_buf *kbuf,
> + u64 buf_min, u64 buf_max,
> + const struct crash_mem *emem)
> +{
> + int i, ret = 0, err = -EADDRNOTAVAIL;
> + u64 start, end, tmin, tmax;
> +
> + tmin = buf_min;
> + for (i = 0; i < emem->nr_ranges; i++) {
> + start = emem->ranges[i].start;
> + end = emem->ranges[i].end;
> +
> + if (end < tmin)
> + continue;
> +
> + if (start > tmin) {
> + tmax = (start > buf_max ? buf_max : start - 1);
> + ret = __locate_mem_hole_ppc64(kbuf, tmin, tmax);
> + if (!ret)
> + return 0;
> + }
> +
> + tmin = end + 1;
> +
> + if (tmin > buf_max) {
> + ret = err;
> + break;
> + }
> + ret = 0;
> + }
> +
> + if (!ret) {
> + tmax = buf_max;
> + ret = __locate_mem_hole_ppc64(kbuf, tmin, tmax);
> + }
> + return ret;
> +}
> +
> +/**
> + * kexec_locate_mem_hole_ppc64 - Skip special memory regions like rtas,
> + * tce-table, opal, reserved-ranges & such
> + * (exclude memory ranges) as they can't be
> + * used for kexec segment buffer. Use buf_min
> + * & buf_max fields in kexec_buf structure to
> + * skip regions. Sets kbuf->mem when a
> + * suitable memory hole is found.
> + * @kbuf: Buffer contents and memory parameters.
> + *
> + * Returns 0 on success, negative errno on error.
> + */
> +static int kexec_locate_mem_hole_ppc64(struct kexec_buf *kbuf)
> +{
> + struct crash_mem **emem;
> + u64 buf_min, buf_max;
> + int ret;
> +
> + /*
> + * Use the locate_mem_hole logic in kexec_add_buffer() for regular
> + * kexec_file_load syscall
> + */
> + if (kbuf->image->type != KEXEC_TYPE_CRASH)
> + return 0;
Can the ranges overlap [crashk_res.start, crashk_res.end]? Otherwise
there is no requirement for @exclude_ranges.
I guess you have a design for future. If not true, then it is better to
fold the condition "if (kbuf->image->type != KEXEC_TYPE_CRASH)" into the
caller and rename this function to better distinguish use cases between
kexec and kdump
Thanks,
Pingfan
> +
> + /* Look up the exclude ranges list while locating the memory hole */
> + emem = &(kbuf->image->arch.exclude_ranges);
> + if (!(*emem) || ((*emem)->nr_ranges == 0)) {
> + pr_warn("No exclude range list. Using the default locate mem hole method\n");
> + return 0;
> + }
> +
> + /* Ensure minimum alignment needed for segments. */
> + kbuf->memsz = ALIGN(kbuf->memsz, PAGE_SIZE);
> + kbuf->buf_align = max(kbuf->buf_align, PAGE_SIZE);
> +
> + /* Segments for kdump kernel should be within crashkernel region */
> + buf_min = (kbuf->buf_min < crashk_res.start ?
> + crashk_res.start : kbuf->buf_min);
> + buf_max = (kbuf->buf_max > crashk_res.end ?
> + crashk_res.end : kbuf->buf_max);
> +
> + if (buf_min > buf_max) {
> + pr_err("Invalid buffer min and/or max values\n");
> + return -EINVAL;
> + }
> +
> + if (kbuf->top_down)
> + ret = locate_mem_hole_top_down_ppc64(kbuf, buf_min, buf_max,
> + *emem);
> + else
> + ret = locate_mem_hole_bottom_up_ppc64(kbuf, buf_min, buf_max,
> + *emem);
> +
> + /* Add the buffer allocated to the exclude list for the next lookup */
> + if (!ret) {
> + add_mem_range(emem, kbuf->mem, kbuf->memsz);
> + sort_memory_ranges(*emem);
> + }
> + return ret;
> +}
> +
> +/**
> * setup_purgatory_ppc64 - initialize PPC64 specific purgatory's global
> * variables and call setup_purgatory() to initialize
> * common global variable.
> @@ -89,6 +332,29 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
> }
>
> /**
> + * arch_kexec_add_buffer - Locate memory hole before calling kexec_add_buffer().
> + * All kexec_add_buffer() callers should use this
> + * function instead.
> + * @kbuf: Buffer contents and memory parameters.
> + *
> + * Returns 0 on success, negative errno on error.
> + */
> +int arch_kexec_add_buffer(struct kexec_buf *kbuf)
> +{
> + int ret;
> +
> + ret = kexec_locate_mem_hole_ppc64(kbuf);
> + if (ret)
> + goto out;
> +
> + ret = __kexec_add_buffer(kbuf);
> +out:
> + if (ret)
> + pr_err("Failed to add buffer of size %lu\n", kbuf->memsz);
> + return ret;
> +}
> +
> +/**
> * arch_kexec_kernel_image_probe - Does additional handling needed to setup
> * kexec segments.
> * @image: kexec image being loaded.
> @@ -100,9 +366,31 @@ int setup_new_fdt_ppc64(const struct kimage *image, void *fdt,
> int arch_kexec_kernel_image_probe(struct kimage *image, void *buf,
> unsigned long buf_len)
> {
> - /* We don't support crash kernels yet. */
> - if (image->type == KEXEC_TYPE_CRASH)
> + if (image->type == KEXEC_TYPE_CRASH) {
> + int ret;
> +
> + /* Get exclude memory ranges needed for setting up kdump segments */
> + ret = get_exclude_memory_ranges(&(image->arch.exclude_ranges));
> + if (ret)
> + pr_err("Failed to setup exclude memory ranges for buffer lookup\n");
> + /* Return this until all changes for panic kernel are in */
> return -EOPNOTSUPP;
> + }
>
> return kexec_image_probe_default(image, buf, buf_len);
> }
> +
> +/**
> + * arch_kimage_file_post_load_cleanup - Frees up all the allocations done
> + * while loading the image.
> + * @image: kexec image being loaded.
> + *
> + * Returns 0 on success, negative errno on error.
> + */
> +int arch_kimage_file_post_load_cleanup(struct kimage *image)
> +{
> + kfree(image->arch.exclude_ranges);
> + image->arch.exclude_ranges = NULL;
> +
> + return kexec_image_post_load_cleanup_default(image);
> +}
>
>
> _______________________________________________
> kexec mailing list
> kexec@lists.infradead.org
> http://lists.infradead.org/mailman/listinfo/kexec
>
^ permalink raw reply
* [PATCH] kbuild: introduce ccflags-remove-y and asflags-remove-y
From: Masahiro Yamada @ 2020-06-28 1:50 UTC (permalink / raw)
To: linux-kbuild
Cc: Michal Marek, Yoshinori Sato, linux-sh, Masahiro Yamada,
linuxppc-dev, linux-kernel, Steven Rostedt, Russell King,
Ingo Molnar, Paul Mackerras, Sami Tolvanen, Rich Felker,
linux-arm-kernel
CFLAGS_REMOVE_<file>.o works per object, that is, there is no
convenient way to filter out flags for every object in a directory.
Add ccflags-remove-y and asflags-remove-y to make it easily.
Use ccflags-remove-y to clean up some Makefiles.
Suggested-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
---
arch/arm/boot/compressed/Makefile | 6 +-----
arch/powerpc/xmon/Makefile | 3 +--
arch/sh/boot/compressed/Makefile | 5 +----
kernel/trace/Makefile | 4 ++--
lib/Makefile | 5 +----
scripts/Makefile.lib | 4 ++--
6 files changed, 8 insertions(+), 19 deletions(-)
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 00602a6fba04..3d5691b23951 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -103,13 +103,9 @@ clean-files += piggy_data lib1funcs.S ashldi3.S bswapsdi2.S hyp-stub.S
KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
-ifeq ($(CONFIG_FUNCTION_TRACER),y)
-ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
-endif
-
ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin \
-I$(obj) $(DISABLE_ARM_SSP_PER_TASK_PLUGIN)
+ccflags-remove-$(CONFIG_FUNCTION_TRACER) += -pg
asflags-y := -DZIMAGE
# Supply kernel BSS size to the decompressor via a linker symbol.
diff --git a/arch/powerpc/xmon/Makefile b/arch/powerpc/xmon/Makefile
index 89c76ca35640..55cbcdd88ac0 100644
--- a/arch/powerpc/xmon/Makefile
+++ b/arch/powerpc/xmon/Makefile
@@ -7,8 +7,7 @@ UBSAN_SANITIZE := n
KASAN_SANITIZE := n
# Disable ftrace for the entire directory
-ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS))
+ccflags-remove-y += $(CC_FLAGS_FTRACE)
ifdef CONFIG_CC_IS_CLANG
# clang stores addresses on the stack causing the frame size to blow
diff --git a/arch/sh/boot/compressed/Makefile b/arch/sh/boot/compressed/Makefile
index ad0e2403e56f..589d2d8a573d 100644
--- a/arch/sh/boot/compressed/Makefile
+++ b/arch/sh/boot/compressed/Makefile
@@ -28,10 +28,7 @@ IMAGE_OFFSET := $(shell /bin/bash -c 'printf "0x%08x" \
$(CONFIG_BOOT_LINK_OFFSET)]')
endif
-ifeq ($(CONFIG_MCOUNT),y)
-ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst -pg, , $(ORIG_CFLAGS))
-endif
+ccflags-remove-$(CONFIG_MCOUNT) += -pg
LDFLAGS_vmlinux := --oformat $(ld-bfd) -Ttext $(IMAGE_OFFSET) -e startup \
-T $(obj)/../../kernel/vmlinux.lds
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 6575bb0a0434..7492844a8b1b 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -2,9 +2,9 @@
# Do not instrument the tracer itself:
+ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)
+
ifdef CONFIG_FUNCTION_TRACER
-ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS))
# Avoid recursion due to instrumentation.
KCSAN_SANITIZE := n
diff --git a/lib/Makefile b/lib/Makefile
index b1c42c10073b..b2ed4beddd68 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -3,10 +3,7 @@
# Makefile for some libs needed in the kernel.
#
-ifdef CONFIG_FUNCTION_TRACER
-ORIG_CFLAGS := $(KBUILD_CFLAGS)
-KBUILD_CFLAGS = $(subst $(CC_FLAGS_FTRACE),,$(ORIG_CFLAGS))
-endif
+ccflags-remove-$(CONFIG_FUNCTION_TRACER) += $(CC_FLAGS_FTRACE)
# These files are disabled because they produce lots of non-interesting and/or
# flaky coverage that is not a function of syscall inputs. For example,
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index 99ac59c59826..5da420f13f9b 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -113,10 +113,10 @@ modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile))
orig_c_flags = $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) \
$(ccflags-y) $(CFLAGS_$(target-stem).o)
-_c_flags = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), $(orig_c_flags))
+_c_flags = $(filter-out $(ccflags-remove-y) $(CFLAGS_REMOVE_$(target-stem).o), $(orig_c_flags))
orig_a_flags = $(KBUILD_CPPFLAGS) $(KBUILD_AFLAGS) \
$(asflags-y) $(AFLAGS_$(target-stem).o)
-_a_flags = $(filter-out $(AFLAGS_REMOVE_$(target-stem).o), $(orig_a_flags))
+_a_flags = $(filter-out $(asflags-remove-y) $(AFLAGS_REMOVE_$(target-stem).o), $(orig_a_flags))
_cpp_flags = $(KBUILD_CPPFLAGS) $(cppflags-y) $(CPPFLAGS_$(target-stem).lds)
#
--
2.25.1
^ permalink raw reply related
* [powerpc:next-test] BUILD SUCCESS 552e738289b6487cd82198369ddd00338b684c0b
From: kernel test robot @ 2020-06-28 1:43 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
tree/branch: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next-test
branch HEAD: 552e738289b6487cd82198369ddd00338b684c0b powerpc/selftest/ptrace-pkey: IAMR and uamor cannot be updated by ptrace
elapsed time: 2179m
configs tested: 148
configs skipped: 8
The following configs have been built successfully.
More configs may be tested in the coming days.
arm defconfig
arm allyesconfig
arm allmodconfig
arm allnoconfig
arm64 allyesconfig
arm64 defconfig
arm64 allmodconfig
arm64 allnoconfig
arc haps_hs_smp_defconfig
s390 allyesconfig
powerpc g5_defconfig
mips jmr3927_defconfig
sh se7751_defconfig
arm imx_v6_v7_defconfig
arm xcep_defconfig
arm pxa255-idp_defconfig
arm tango4_defconfig
arm cm_x300_defconfig
sh microdev_defconfig
m68k allmodconfig
powerpc ppc64_defconfig
h8300 allyesconfig
arc defconfig
arm lart_defconfig
m68k atari_defconfig
arm mini2440_defconfig
arm pxa168_defconfig
arm pxa_defconfig
arm lpc18xx_defconfig
mips ip27_defconfig
arm eseries_pxa_defconfig
mips loongson3_defconfig
m68k alldefconfig
nios2 10m50_defconfig
mips decstation_defconfig
arm versatile_defconfig
mips ath25_defconfig
mips nlm_xlp_defconfig
sparc allyesconfig
arm netwinder_defconfig
mips maltaup_xpa_defconfig
powerpc gamecube_defconfig
ia64 defconfig
h8300 h8s-sim_defconfig
sh landisk_defconfig
sh kfr2r09_defconfig
mips maltasmvp_eva_defconfig
sh apsh4a3a_defconfig
openrisc or1ksim_defconfig
arm axm55xx_defconfig
mips pistachio_defconfig
arm ixp4xx_defconfig
arm spear13xx_defconfig
i386 alldefconfig
nds32 allnoconfig
sh se7724_defconfig
mips loongson1b_defconfig
parisc allnoconfig
mips jazz_defconfig
x86_64 alldefconfig
arm s3c2410_defconfig
powerpc mpc512x_defconfig
openrisc simple_smp_defconfig
sh cayman_defconfig
arm bcm2835_defconfig
sh sh7785lcr_32bit_defconfig
i386 allnoconfig
i386 allyesconfig
i386 defconfig
i386 debian-10.3
ia64 allmodconfig
ia64 allnoconfig
ia64 allyesconfig
m68k allnoconfig
m68k sun3_defconfig
m68k defconfig
m68k allyesconfig
nios2 defconfig
nios2 allyesconfig
openrisc defconfig
c6x allyesconfig
c6x allnoconfig
openrisc allyesconfig
nds32 defconfig
csky allyesconfig
csky defconfig
alpha defconfig
alpha allyesconfig
xtensa allyesconfig
h8300 allmodconfig
xtensa defconfig
arc allyesconfig
sh allmodconfig
sh allnoconfig
microblaze allnoconfig
mips allyesconfig
mips allnoconfig
mips allmodconfig
parisc defconfig
parisc allyesconfig
parisc allmodconfig
powerpc defconfig
powerpc allyesconfig
powerpc rhel-kconfig
powerpc allmodconfig
powerpc allnoconfig
i386 randconfig-a002-20200624
i386 randconfig-a006-20200624
i386 randconfig-a003-20200624
i386 randconfig-a001-20200624
i386 randconfig-a005-20200624
i386 randconfig-a004-20200624
x86_64 randconfig-a004-20200624
x86_64 randconfig-a002-20200624
x86_64 randconfig-a003-20200624
x86_64 randconfig-a005-20200624
x86_64 randconfig-a001-20200624
x86_64 randconfig-a006-20200624
i386 randconfig-a013-20200624
i386 randconfig-a016-20200624
i386 randconfig-a012-20200624
i386 randconfig-a014-20200624
i386 randconfig-a011-20200624
i386 randconfig-a015-20200624
riscv allyesconfig
riscv allnoconfig
riscv defconfig
riscv allmodconfig
s390 allnoconfig
s390 allmodconfig
s390 defconfig
sparc defconfig
sparc64 defconfig
sparc64 allnoconfig
sparc64 allyesconfig
sparc64 allmodconfig
um allmodconfig
um allnoconfig
um defconfig
um allyesconfig
x86_64 rhel-7.6
x86_64 rhel-7.6-kselftests
x86_64 rhel-8.3
x86_64 kexec
x86_64 rhel
x86_64 rhel-7.2-clear
x86_64 lkp
x86_64 fedora-25
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
^ permalink raw reply
* [powerpc:fixes-test] BUILD SUCCESS 896066aa0685af3434637998b76218c2045142a8
From: kernel test robot @ 2020-06-28 1:43 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
tree/branch: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git fixes-test
branch HEAD: 896066aa0685af3434637998b76218c2045142a8 selftests/powerpc: Fix build failure in ebb tests
elapsed time: 2777m
configs tested: 159
configs skipped: 7
The following configs have been built successfully.
More configs may be tested in the coming days.
arm defconfig
arm allyesconfig
arm allmodconfig
arm allnoconfig
arm64 allyesconfig
arm64 defconfig
arm64 allmodconfig
arm64 allnoconfig
arc haps_hs_smp_defconfig
s390 allyesconfig
powerpc g5_defconfig
mips jmr3927_defconfig
sh se7751_defconfig
arm imx_v6_v7_defconfig
arm xcep_defconfig
arm pxa255-idp_defconfig
arm tango4_defconfig
arm cm_x300_defconfig
sh microdev_defconfig
m68k allmodconfig
powerpc ppc64_defconfig
arm pxa_defconfig
arm lpc18xx_defconfig
mips ip27_defconfig
arm eseries_pxa_defconfig
mips loongson3_defconfig
m68k alldefconfig
nios2 10m50_defconfig
mips decstation_defconfig
arm versatile_defconfig
mips ath25_defconfig
mips nlm_xlp_defconfig
sparc allyesconfig
arm netwinder_defconfig
mips maltaup_xpa_defconfig
powerpc gamecube_defconfig
h8300 h8s-sim_defconfig
sh landisk_defconfig
sh kfr2r09_defconfig
mips maltasmvp_eva_defconfig
sh apsh4a3a_defconfig
openrisc or1ksim_defconfig
i386 alldefconfig
sh se7724_defconfig
mips loongson1b_defconfig
nds32 allnoconfig
parisc allnoconfig
arm lart_defconfig
mips jazz_defconfig
x86_64 alldefconfig
arm s3c2410_defconfig
powerpc mpc512x_defconfig
openrisc simple_smp_defconfig
sh cayman_defconfig
arm bcm2835_defconfig
sh sh7785lcr_32bit_defconfig
i386 allnoconfig
i386 allyesconfig
i386 defconfig
i386 debian-10.3
ia64 allmodconfig
ia64 defconfig
ia64 allnoconfig
ia64 allyesconfig
m68k allnoconfig
m68k sun3_defconfig
m68k defconfig
m68k allyesconfig
nios2 defconfig
nios2 allyesconfig
openrisc defconfig
c6x allyesconfig
c6x allnoconfig
openrisc allyesconfig
nds32 defconfig
csky allyesconfig
csky defconfig
alpha defconfig
alpha allyesconfig
xtensa allyesconfig
h8300 allyesconfig
h8300 allmodconfig
xtensa defconfig
arc defconfig
arc allyesconfig
sh allmodconfig
sh allnoconfig
microblaze allnoconfig
mips allyesconfig
mips allnoconfig
mips allmodconfig
parisc defconfig
parisc allyesconfig
parisc allmodconfig
powerpc defconfig
powerpc allyesconfig
powerpc rhel-kconfig
powerpc allmodconfig
powerpc allnoconfig
x86_64 randconfig-a004-20200624
x86_64 randconfig-a002-20200624
x86_64 randconfig-a003-20200624
x86_64 randconfig-a005-20200624
x86_64 randconfig-a001-20200624
x86_64 randconfig-a006-20200624
x86_64 randconfig-a002-20200628
x86_64 randconfig-a004-20200628
x86_64 randconfig-a003-20200628
x86_64 randconfig-a005-20200628
x86_64 randconfig-a001-20200628
x86_64 randconfig-a006-20200628
i386 randconfig-a002-20200624
i386 randconfig-a006-20200624
i386 randconfig-a003-20200624
i386 randconfig-a001-20200624
i386 randconfig-a005-20200624
i386 randconfig-a004-20200624
i386 randconfig-a006-20200628
i386 randconfig-a002-20200628
i386 randconfig-a003-20200628
i386 randconfig-a001-20200628
i386 randconfig-a005-20200628
i386 randconfig-a004-20200628
i386 randconfig-a013-20200624
i386 randconfig-a016-20200624
i386 randconfig-a012-20200624
i386 randconfig-a014-20200624
i386 randconfig-a011-20200624
i386 randconfig-a015-20200624
i386 randconfig-a013-20200628
i386 randconfig-a016-20200628
i386 randconfig-a014-20200628
i386 randconfig-a012-20200628
i386 randconfig-a015-20200628
i386 randconfig-a011-20200628
riscv allyesconfig
riscv allnoconfig
riscv defconfig
riscv allmodconfig
s390 allnoconfig
s390 allmodconfig
s390 defconfig
sparc defconfig
sparc64 defconfig
sparc64 allnoconfig
sparc64 allyesconfig
sparc64 allmodconfig
um allmodconfig
um allnoconfig
um defconfig
um allyesconfig
x86_64 rhel-7.6
x86_64 rhel-7.6-kselftests
x86_64 rhel-8.3
x86_64 kexec
x86_64 rhel
x86_64 rhel-7.2-clear
x86_64 lkp
x86_64 fedora-25
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
^ permalink raw reply
* [powerpc:merge] BUILD SUCCESS f66ebd048174992db612ec8157c83f6c6601e8b0
From: kernel test robot @ 2020-06-28 1:43 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
tree/branch: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git merge
branch HEAD: f66ebd048174992db612ec8157c83f6c6601e8b0 Automatic merge of 'master', 'next' and 'fixes' (2020-06-27 21:56)
elapsed time: 822m
configs tested: 139
configs skipped: 6
The following configs have been built successfully.
More configs may be tested in the coming days.
arm defconfig
arm allyesconfig
arm allmodconfig
arm allnoconfig
arm64 allyesconfig
arm64 defconfig
arm64 allmodconfig
arm64 allnoconfig
arc haps_hs_smp_defconfig
powerpc g5_defconfig
mips jmr3927_defconfig
sh se7751_defconfig
arm imx_v6_v7_defconfig
arm xcep_defconfig
arm pxa255-idp_defconfig
arm tango4_defconfig
arm cm_x300_defconfig
sh microdev_defconfig
m68k allmodconfig
powerpc ppc64_defconfig
h8300 allyesconfig
arc defconfig
m68k atari_defconfig
arm mini2440_defconfig
arm pxa168_defconfig
m68k alldefconfig
nios2 10m50_defconfig
mips decstation_defconfig
arm versatile_defconfig
mips ath25_defconfig
mips nlm_xlp_defconfig
sparc allyesconfig
arm netwinder_defconfig
mips maltaup_xpa_defconfig
powerpc gamecube_defconfig
ia64 defconfig
h8300 h8s-sim_defconfig
sh landisk_defconfig
sh kfr2r09_defconfig
mips maltasmvp_eva_defconfig
sh apsh4a3a_defconfig
openrisc or1ksim_defconfig
i386 alldefconfig
sh se7724_defconfig
mips loongson1b_defconfig
parisc allnoconfig
arm lart_defconfig
mips loongson3_defconfig
mips jazz_defconfig
x86_64 alldefconfig
arm s3c2410_defconfig
powerpc mpc512x_defconfig
openrisc simple_smp_defconfig
sh cayman_defconfig
arm bcm2835_defconfig
sh sh7785lcr_32bit_defconfig
i386 allnoconfig
i386 allyesconfig
i386 defconfig
i386 debian-10.3
ia64 allmodconfig
ia64 allnoconfig
ia64 allyesconfig
m68k allnoconfig
m68k sun3_defconfig
m68k defconfig
m68k allyesconfig
nios2 defconfig
nios2 allyesconfig
openrisc defconfig
c6x allyesconfig
c6x allnoconfig
openrisc allyesconfig
nds32 defconfig
nds32 allnoconfig
csky allyesconfig
csky defconfig
alpha defconfig
alpha allyesconfig
xtensa allyesconfig
h8300 allmodconfig
xtensa defconfig
arc allyesconfig
sh allmodconfig
sh allnoconfig
microblaze allnoconfig
mips allyesconfig
mips allnoconfig
mips allmodconfig
parisc defconfig
parisc allyesconfig
parisc allmodconfig
powerpc allyesconfig
powerpc rhel-kconfig
powerpc allmodconfig
powerpc allnoconfig
powerpc defconfig
i386 randconfig-a002-20200624
i386 randconfig-a006-20200624
i386 randconfig-a003-20200624
i386 randconfig-a001-20200624
i386 randconfig-a005-20200624
i386 randconfig-a004-20200624
x86_64 randconfig-a004-20200624
x86_64 randconfig-a002-20200624
x86_64 randconfig-a003-20200624
x86_64 randconfig-a005-20200624
x86_64 randconfig-a001-20200624
x86_64 randconfig-a006-20200624
i386 randconfig-a013-20200624
i386 randconfig-a016-20200624
i386 randconfig-a012-20200624
i386 randconfig-a011-20200624
i386 randconfig-a015-20200624
riscv allyesconfig
riscv allnoconfig
riscv defconfig
riscv allmodconfig
s390 allyesconfig
s390 allnoconfig
s390 allmodconfig
s390 defconfig
sparc defconfig
sparc64 defconfig
sparc64 allnoconfig
sparc64 allyesconfig
sparc64 allmodconfig
um allnoconfig
um allyesconfig
um defconfig
um allmodconfig
x86_64 rhel-7.6
x86_64 rhel-7.6-kselftests
x86_64 rhel-8.3
x86_64 kexec
x86_64 rhel
x86_64 rhel-7.2-clear
x86_64 lkp
x86_64 fedora-25
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
^ permalink raw reply
* Re: [PATCH 2/8] opeinrisc: switch to generic version of pte allocation
From: Stafford Horne @ 2020-06-27 21:23 UTC (permalink / raw)
To: Mike Rapoport
Cc: linux-ia64, linux-sh, Peter Zijlstra, linux-mips, Max Filippov,
Satheesh Rajendran, linux-csky, sparclinux, linux-riscv,
linux-arch, Stephen Rothwell, linux-hexagon, Joerg Roedel,
Mike Rapoport, Abdul Haleem, linux-snps-arc, linux-xtensa,
Arnd Bergmann, linux-s390, linux-um, Steven Rostedt, linux-m68k,
openrisc, Andy Lutomirski, linux-arm-kernel, linux-parisc,
linux-mm, linux-kernel, linux-alpha, Andrew Morton, linuxppc-dev
In-Reply-To: <20200627143453.31835-3-rppt@kernel.org>
On Sat, Jun 27, 2020 at 05:34:47PM +0300, Mike Rapoport wrote:
> From: Mike Rapoport <rppt@linux.ibm.com>
>
> Replace pte_alloc_one(), pte_free() and pte_free_kernel() with the generic
> implementation. The only actual functional change is the addition of
> __GFP_ACCOUT for the allocation of the user page tables.
>
> The pte_alloc_one_kernel() is kept back because its implementation on
> openrisc is different than the generic one.
>
> Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
Thank's for this.
Acked-by: Stafford Horne <shorne@gmail.com>
^ permalink raw reply
* Re: [PATCH 1/3] powerpc: inline doorbell sending functions
From: kernel test robot @ 2020-06-27 19:46 UTC (permalink / raw)
To: Nicholas Piggin, linuxppc-dev
Cc: kvm-ppc, kbuild-all, Nicholas Piggin, Anton Blanchard,
Cédric Le Goater, David Gibson
In-Reply-To: <20200627150428.2525192-2-npiggin@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 5147 bytes --]
Hi Nicholas,
I love your patch! Yet something to improve:
[auto build test ERROR on powerpc/next]
[also build test ERROR on scottwood/next v5.8-rc2 next-20200626]
[cannot apply to kvm-ppc/kvm-ppc-next]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use as documented in
https://git-scm.com/docs/git-format-patch]
url: https://github.com/0day-ci/linux/commits/Nicholas-Piggin/powerpc-pseries-IPI-doorbell-improvements/20200627-230544
base: https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git next
config: powerpc-randconfig-c003-20200628 (attached as .config)
compiler: powerpc64-linux-gcc (GCC) 9.3.0
If you fix the issue, kindly add following tag as appropriate
Reported-by: kernel test robot <lkp@intel.com>
All error/warnings (new ones prefixed by >>):
In file included from arch/powerpc/kernel/asm-offsets.c:38:
arch/powerpc/include/asm/dbell.h: In function 'doorbell_global_ipi':
>> arch/powerpc/include/asm/dbell.h:114:12: error: implicit declaration of function 'get_hard_smp_processor_id'; did you mean 'raw_smp_processor_id'? [-Werror=implicit-function-declaration]
114 | u32 tag = get_hard_smp_processor_id(cpu);
| ^~~~~~~~~~~~~~~~~~~~~~~~~
| raw_smp_processor_id
arch/powerpc/include/asm/dbell.h: In function 'doorbell_try_core_ipi':
>> arch/powerpc/include/asm/dbell.h:146:28: error: implicit declaration of function 'cpu_sibling_mask'; did you mean 'cpu_online_mask'? [-Werror=implicit-function-declaration]
146 | if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) {
| ^~~~~~~~~~~~~~~~
| cpu_online_mask
>> arch/powerpc/include/asm/dbell.h:146:28: warning: passing argument 2 of 'cpumask_test_cpu' makes pointer from integer without a cast [-Wint-conversion]
146 | if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) {
| ^~~~~~~~~~~~~~~~~~~~~~~~~~
| |
| int
In file included from include/linux/workqueue.h:15,
from include/linux/rhashtable-types.h:15,
from include/linux/ipc.h:7,
from include/uapi/linux/sem.h:5,
from include/linux/sem.h:5,
from include/linux/compat.h:14,
from arch/powerpc/kernel/asm-offsets.c:14:
include/linux/cpumask.h:365:67: note: expected 'const struct cpumask *' but argument is of type 'int'
365 | static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
| ~~~~~~~~~~~~~~~~~~~~~~^~~~~~~
cc1: some warnings being treated as errors
make[2]: *** [scripts/Makefile.build:114: arch/powerpc/kernel/asm-offsets.s] Error 1
make[2]: Target '__build' not remade because of errors.
make[1]: *** [Makefile:1175: prepare0] Error 2
make[1]: Target 'prepare' not remade because of errors.
make: *** [Makefile:185: __sub-make] Error 2
make: Target 'prepare' not remade because of errors.
vim +114 arch/powerpc/include/asm/dbell.h
100
101 /*
102 * Doorbells must only be used if CPU_FTR_DBELL is available.
103 * msgsnd is used in HV, and msgsndp is used in !HV.
104 *
105 * These should be used by platform code that is aware of restrictions.
106 * Other arch code should use ->cause_ipi.
107 *
108 * doorbell_global_ipi() sends a dbell to any target CPU.
109 * Must be used only by architectures that address msgsnd target
110 * by PIR/get_hard_smp_processor_id.
111 */
112 static inline void doorbell_global_ipi(int cpu)
113 {
> 114 u32 tag = get_hard_smp_processor_id(cpu);
115
116 kvmppc_set_host_ipi(cpu);
117 /* Order previous accesses vs. msgsnd, which is treated as a store */
118 ppc_msgsnd_sync();
119 ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
120 }
121
122 /*
123 * doorbell_core_ipi() sends a dbell to a target CPU in the same core.
124 * Must be used only by architectures that address msgsnd target
125 * by TIR/cpu_thread_in_core.
126 */
127 static inline void doorbell_core_ipi(int cpu)
128 {
129 u32 tag = cpu_thread_in_core(cpu);
130
131 kvmppc_set_host_ipi(cpu);
132 /* Order previous accesses vs. msgsnd, which is treated as a store */
133 ppc_msgsnd_sync();
134 ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
135 }
136
137 /*
138 * Attempt to cause a core doorbell if destination is on the same core.
139 * Returns 1 on success, 0 on failure.
140 */
141 static inline int doorbell_try_core_ipi(int cpu)
142 {
143 int this_cpu = get_cpu();
144 int ret = 0;
145
> 146 if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) {
147 doorbell_core_ipi(cpu);
148 ret = 1;
149 }
150
151 put_cpu();
152
153 return ret;
154 }
155
---
0-DAY CI Kernel Test Service, Intel Corporation
https://lists.01.org/hyperkitty/list/kbuild-all@lists.01.org
[-- Attachment #2: .config.gz --]
[-- Type: application/gzip, Size: 25869 bytes --]
^ permalink raw reply
* Re: [PATCH 4/8] asm-generic: pgalloc: provide generic pmd_alloc_one() and pmd_free_one()
From: Matthew Wilcox @ 2020-06-27 19:03 UTC (permalink / raw)
To: Mike Rapoport
Cc: linux-ia64, linux-sh, Peter Zijlstra, linux-mips, Max Filippov,
Satheesh Rajendran, linux-csky, sparclinux, linux-riscv,
linux-arch, Stephen Rothwell, linux-hexagon, Joerg Roedel,
Mike Rapoport, Abdul Haleem, linux-snps-arc, linux-xtensa,
Arnd Bergmann, linux-s390, linux-um, Steven Rostedt, linux-m68k,
openrisc, Andy Lutomirski, Stafford Horne, linux-arm-kernel,
linux-parisc, linux-mm, linux-kernel, linux-alpha, Andrew Morton,
linuxppc-dev
In-Reply-To: <20200627143453.31835-5-rppt@kernel.org>
On Sat, Jun 27, 2020 at 05:34:49PM +0300, Mike Rapoport wrote:
> More elaborate versions on arm64 and x86 account memory for the user page
> tables and call to pgtable_pmd_page_ctor() as the part of PMD page
> initialization.
>
> Move the arm64 version to include/asm-generic/pgalloc.h and use the generic
> version on several architectures.
>
> The pgtable_pmd_page_ctor() is a NOP when ARCH_ENABLE_SPLIT_PMD_PTLOCK is
> not enabled, so there is no functional change for most architectures except
> of the addition of __GFP_ACCOUNT for allocation of user page tables.
Thanks for including this line; it reminded me that we're not setting
the PageTable flag on the page, nor accounting it to the zone page stats.
Hope you don't mind me tagging a patch to do that on as 9/8.
We could also do with a pud_page_[cd]tor and maybe even p4d/pgd versions.
But that brings me to the next question -- could/should some of this
be moved over to asm-generic/pgalloc.h? The ctor/dtor aren't called
from anywhere else, and there's value to reducing the total amount of
code in mm.h, but then there's also value to keeping all the ifdef
ARCH_ENABLE_SPLIT_PMD_PTLOCK code together too. So I'm a bit torn.
What do you think?
^ permalink raw reply
* [PATCH 9/8] mm: Account PMD tables like PTE tables
From: Matthew Wilcox @ 2020-06-27 18:46 UTC (permalink / raw)
To: Mike Rapoport
Cc: linux-ia64, linux-sh, Peter Zijlstra, linux-mips, Max Filippov,
Satheesh Rajendran, linux-csky, sparclinux, linux-riscv,
linux-arch, Stephen Rothwell, linux-hexagon, Joerg Roedel,
Mike Rapoport, Abdul Haleem, linux-snps-arc, linux-xtensa,
Arnd Bergmann, linux-s390, linux-um, Steven Rostedt, linux-m68k,
openrisc, Andy Lutomirski, Stafford Horne, linux-arm-kernel,
linux-parisc, linux-mm, linux-kernel, linux-alpha, Andrew Morton,
linuxppc-dev
In-Reply-To: <20200627143453.31835-1-rppt@kernel.org>
We account the PTE level of the page tables to the process in order to
make smarter OOM decisions and help diagnose why memory is fragmented.
For these same reasons, we should account pages allocated for PMDs.
With larger process address spaces and ASLR, the number of PMDs in use
is higher than it used to be so the inaccuracy is starting to matter.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
include/linux/mm.h | 24 ++++++++++++++++++++----
1 file changed, 20 insertions(+), 4 deletions(-)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index dc7b87310c10..b283e25fcffa 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2271,7 +2271,7 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
return ptlock_ptr(pmd_to_page(pmd));
}
-static inline bool pgtable_pmd_page_ctor(struct page *page)
+static inline bool pmd_ptlock_init(struct page *page)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
page->pmd_huge_pte = NULL;
@@ -2279,7 +2279,7 @@ static inline bool pgtable_pmd_page_ctor(struct page *page)
return ptlock_init(page);
}
-static inline void pgtable_pmd_page_dtor(struct page *page)
+static inline void pmd_ptlock_free(struct page *page)
{
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
VM_BUG_ON_PAGE(page->pmd_huge_pte, page);
@@ -2296,8 +2296,8 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
return &mm->page_table_lock;
}
-static inline bool pgtable_pmd_page_ctor(struct page *page) { return true; }
-static inline void pgtable_pmd_page_dtor(struct page *page) {}
+static inline bool pmd_ptlock_init(struct page *page) { return true; }
+static inline void pmd_ptlock_free(struct page *page) {}
#define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
@@ -2310,6 +2310,22 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
return ptl;
}
+static inline bool pgtable_pmd_page_ctor(struct page *page)
+{
+ if (!pmd_ptlock_init(page))
+ return false;
+ __SetPageTable(page);
+ inc_zone_page_state(page, NR_PAGETABLE);
+ return true;
+}
+
+static inline void pgtable_pmd_page_dtor(struct page *page)
+{
+ pmd_ptlock_free(page);
+ __ClearPageTable(page);
+ dec_zone_page_state(page, NR_PAGETABLE);
+}
+
/*
* No scalability reason to split PUD locks yet, but follow the same pattern
* as the PMD locks to make it easier if we decide to. The VM should not be
--
2.27.0
^ permalink raw reply related
* Re: [PATCH 0/8] mm: cleanup usage of <asm/pgalloc.h>
From: Matthew Wilcox @ 2020-06-27 18:31 UTC (permalink / raw)
To: Mike Rapoport
Cc: linux-ia64, linux-sh, Peter Zijlstra, linux-mips, Max Filippov,
Satheesh Rajendran, linux-csky, sparclinux, linux-riscv,
linux-arch, Stephen Rothwell, linux-hexagon, Joerg Roedel,
Mike Rapoport, Abdul Haleem, linux-snps-arc, linux-xtensa,
Arnd Bergmann, linux-s390, linux-um, Steven Rostedt, linux-m68k,
openrisc, Andy Lutomirski, Stafford Horne, linux-arm-kernel,
linux-parisc, linux-mm, linux-kernel, linux-alpha, Andrew Morton,
linuxppc-dev
In-Reply-To: <20200627143453.31835-1-rppt@kernel.org>
On Sat, Jun 27, 2020 at 05:34:45PM +0300, Mike Rapoport wrote:
> Most architectures have very similar versions of pXd_alloc_one() and
> pXd_free_one() for intermediate levels of page table.
> These patches add generic versions of these functions in
> <asm-generic/pgalloc.h> and enable use of the generic functions where
> appropriate.
For the series:
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
^ permalink raw reply
* Re: [GIT PULL] Please pull powerpc/linux.git powerpc-5.8-4 tag
From: pr-tracker-bot @ 2020-06-27 16:00 UTC (permalink / raw)
To: Michael Ellerman
Cc: aneesh.kumar, linux-kernel, oss, Linus Torvalds, asolokha, harish,
linuxppc-dev
In-Reply-To: <87h7uwbtn3.fsf@mpe.ellerman.id.au>
The pull request you sent on Sat, 27 Jun 2020 22:06:08 +1000:
> https://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux.git tags/powerpc-5.8-4
has been merged into torvalds/linux.git:
https://git.kernel.org/torvalds/c/21d2f6850c09fdec730c11d35406da1dc541432d
Thank you!
--
Deet-doot-dot, I am a bot.
https://korg.wiki.kernel.org/userdoc/prtracker
^ permalink raw reply
* [PATCH 3/3] powerpc/pseries: Add KVM guest doorbell restrictions
From: Nicholas Piggin @ 2020-06-27 15:04 UTC (permalink / raw)
To: linuxppc-dev
Cc: Nicholas Piggin, kvm-ppc, Anton Blanchard, Cédric Le Goater,
David Gibson
In-Reply-To: <20200627150428.2525192-1-npiggin@gmail.com>
KVM guests have certain restrictions and performance quirks when
using doorbells. This patch tests for KVM environment in doorbell
setup, and optimises IPI performance:
- PowerVM guests may now use doorbells even if they are secure.
- KVM guests no longer use doorbells if XIVE is available.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/firmware.h | 2 ++
arch/powerpc/include/asm/kvm_para.h | 26 ++--------------
arch/powerpc/platforms/pseries/firmware.c | 14 +++++++++
arch/powerpc/platforms/pseries/smp.c | 38 ++++++++++++++---------
4 files changed, 42 insertions(+), 38 deletions(-)
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 6003c2e533a0..4dadb84ff2b2 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -134,7 +134,9 @@ extern unsigned int __start___fw_ftr_fixup, __stop___fw_ftr_fixup;
#ifdef CONFIG_PPC_PSERIES
void pseries_probe_fw_features(void);
+bool is_kvm_guest(void);
#else
+static inline bool is_kvm_guest(void) { return false; }
static inline void pseries_probe_fw_features(void) { };
#endif
diff --git a/arch/powerpc/include/asm/kvm_para.h b/arch/powerpc/include/asm/kvm_para.h
index 9c1f6b4b9bbf..744612054c94 100644
--- a/arch/powerpc/include/asm/kvm_para.h
+++ b/arch/powerpc/include/asm/kvm_para.h
@@ -8,35 +8,15 @@
#ifndef __POWERPC_KVM_PARA_H__
#define __POWERPC_KVM_PARA_H__
-#include <uapi/asm/kvm_para.h>
-
-#ifdef CONFIG_KVM_GUEST
-
-#include <linux/of.h>
-
-static inline int kvm_para_available(void)
-{
- struct device_node *hyper_node;
-
- hyper_node = of_find_node_by_path("/hypervisor");
- if (!hyper_node)
- return 0;
+#include <asm/firmware.h>
- if (!of_device_is_compatible(hyper_node, "linux,kvm"))
- return 0;
-
- return 1;
-}
-
-#else
+#include <uapi/asm/kvm_para.h>
static inline int kvm_para_available(void)
{
- return 0;
+ return IS_ENABLED(CONFIG_KVM_GUEST) && is_kvm_guest();
}
-#endif
-
static inline unsigned int kvm_arch_para_features(void)
{
unsigned long r;
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index 3e49cc23a97a..f58eb10011dd 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -184,3 +184,17 @@ void __init pseries_probe_fw_features(void)
{
of_scan_flat_dt(probe_fw_features, NULL);
}
+
+bool is_kvm_guest(void)
+{
+ struct device_node *hyper_node;
+
+ hyper_node = of_find_node_by_path("/hypervisor");
+ if (!hyper_node)
+ return 0;
+
+ if (!of_device_is_compatible(hyper_node, "linux,kvm"))
+ return 0;
+
+ return 1;
+}
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 67e6ad5076ce..7af0003b40b6 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -236,24 +236,32 @@ static __init void pSeries_smp_probe(void)
if (!cpu_has_feature(CPU_FTR_SMT))
return;
- /*
- * KVM emulates doorbells by disabling FSCR[MSGP] so msgsndp faults
- * to the hypervisor which then reads the instruction from guest
- * memory. This can't be done if the guest is secure, so don't use
- * doorbells in secure guests.
- *
- * Under PowerVM, FSCR[MSGP] is enabled so doorbells could be used
- * by secure guests if we distinguished this from KVM.
- */
- if (is_secure_guest())
- return;
+ if (is_kvm_guest()) {
+ /*
+ * KVM emulates doorbells by disabling FSCR[MSGP] so msgsndp
+ * faults to the hypervisor which then reads the instruction
+ * from guest memory, which tends to be slower than using XIVE.
+ */
+ if (xive_enabled())
+ return;
+
+ /*
+ * XICS hcalls aren't as fast, so we can use msgsndp (which
+ * also helps exercise KVM emulation), however KVM can't
+ * emulate secure guests because it can't read the instruction
+ * out of their memory.
+ */
+ if (is_secure_guest())
+ return;
+ }
/*
- * The guest can use doobells for SMT sibling IPIs, which stay in
- * the core rather than going to the interrupt controller. This
- * tends to be slower under KVM where doorbells are emulated, but
- * faster for PowerVM where they're enabled.
+ * Under PowerVM, FSCR[MSGP] is enabled as guest vCPU siblings are
+ * gang scheduled on the same physical core, so doorbells are always
+ * faster than the interrupt controller, and they can be used by
+ * secure guests.
*/
+
ic_cause_ipi = smp_ops->cause_ipi;
smp_ops->cause_ipi = dbell_or_ic_cause_ipi;
}
--
2.23.0
^ permalink raw reply related
* [PATCH 2/3] powerpc/pseries: Use doorbells even if XIVE is available
From: Nicholas Piggin @ 2020-06-27 15:04 UTC (permalink / raw)
To: linuxppc-dev
Cc: Nicholas Piggin, kvm-ppc, Anton Blanchard, Cédric Le Goater,
David Gibson
In-Reply-To: <20200627150428.2525192-1-npiggin@gmail.com>
KVM supports msgsndp in guests by trapping and emulating the
instruction, so it was decided to always use XIVE for IPIs if it is
available. However on PowerVM systems, msgsndp can be used and gives
better performance. On large systems, high XIVE interrupt rates can
have sub-linear scaling, and using msgsndp can reduce the load on
the interrupt controller.
So switch to using core local doorbells even if XIVE is available.
This reduces performance for KVM guests with an SMT topology by
about 50% for ping-pong context switching between SMT vCPUs. An
option vector (or dt-cpu-ftrs) could be defined to disable msgsndp
to get KVM performance back.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/platforms/pseries/smp.c | 54 ++++++++++++++++++----------
1 file changed, 36 insertions(+), 18 deletions(-)
diff --git a/arch/powerpc/platforms/pseries/smp.c b/arch/powerpc/platforms/pseries/smp.c
index 6891710833be..67e6ad5076ce 100644
--- a/arch/powerpc/platforms/pseries/smp.c
+++ b/arch/powerpc/platforms/pseries/smp.c
@@ -188,13 +188,16 @@ static int pseries_smp_prepare_cpu(int cpu)
return 0;
}
-static void smp_pseries_cause_ipi(int cpu)
+/* Cause IPI as setup by the interrupt controller (xics or xive) */
+static void (*ic_cause_ipi)(int cpu) __ro_after_init;
+
+/* Use msgsndp doorbells target is a sibling, else use interrupt controller */
+static void dbell_or_ic_cause_ipi(int cpu)
{
- /* POWER9 should not use this handler */
if (doorbell_try_core_ipi(cpu))
return;
- icp_ops->cause_ipi(cpu);
+ ic_cause_ipi(cpu);
}
static int pseries_cause_nmi_ipi(int cpu)
@@ -218,26 +221,41 @@ static int pseries_cause_nmi_ipi(int cpu)
return 0;
}
-static __init void pSeries_smp_probe_xics(void)
-{
- xics_smp_probe();
-
- if (cpu_has_feature(CPU_FTR_DBELL) && !is_secure_guest())
- smp_ops->cause_ipi = smp_pseries_cause_ipi;
- else
- smp_ops->cause_ipi = icp_ops->cause_ipi;
-}
-
static __init void pSeries_smp_probe(void)
{
if (xive_enabled())
- /*
- * Don't use P9 doorbells when XIVE is enabled. IPIs
- * using MMIOs should be faster
- */
xive_smp_probe();
else
- pSeries_smp_probe_xics();
+ xics_smp_probe();
+
+ /* No doorbell facility, must use the interrupt controller for IPIs */
+ if (!cpu_has_feature(CPU_FTR_DBELL))
+ return;
+
+ /* Doorbells can only be used for IPIs between SMT siblings */
+ if (!cpu_has_feature(CPU_FTR_SMT))
+ return;
+
+ /*
+ * KVM emulates doorbells by disabling FSCR[MSGP] so msgsndp faults
+ * to the hypervisor which then reads the instruction from guest
+ * memory. This can't be done if the guest is secure, so don't use
+ * doorbells in secure guests.
+ *
+ * Under PowerVM, FSCR[MSGP] is enabled so doorbells could be used
+ * by secure guests if we distinguished this from KVM.
+ */
+ if (is_secure_guest())
+ return;
+
+ /*
+ * The guest can use doobells for SMT sibling IPIs, which stay in
+ * the core rather than going to the interrupt controller. This
+ * tends to be slower under KVM where doorbells are emulated, but
+ * faster for PowerVM where they're enabled.
+ */
+ ic_cause_ipi = smp_ops->cause_ipi;
+ smp_ops->cause_ipi = dbell_or_ic_cause_ipi;
}
static struct smp_ops_t pseries_smp_ops = {
--
2.23.0
^ permalink raw reply related
* [PATCH 1/3] powerpc: inline doorbell sending functions
From: Nicholas Piggin @ 2020-06-27 15:04 UTC (permalink / raw)
To: linuxppc-dev
Cc: Nicholas Piggin, kvm-ppc, Anton Blanchard, Cédric Le Goater,
David Gibson
In-Reply-To: <20200627150428.2525192-1-npiggin@gmail.com>
These are only called in one place for a given platform, so inline them
for performance.
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
arch/powerpc/include/asm/dbell.h | 59 ++++++++++++++++++++++++++++++--
arch/powerpc/kernel/dbell.c | 55 -----------------------------
2 files changed, 56 insertions(+), 58 deletions(-)
diff --git a/arch/powerpc/include/asm/dbell.h b/arch/powerpc/include/asm/dbell.h
index 4ce6808deed3..5c9625e5070b 100644
--- a/arch/powerpc/include/asm/dbell.h
+++ b/arch/powerpc/include/asm/dbell.h
@@ -13,6 +13,7 @@
#include <asm/ppc-opcode.h>
#include <asm/feature-fixups.h>
+#include <asm/kvm_ppc.h>
#define PPC_DBELL_MSG_BRDCAST (0x04000000)
#define PPC_DBELL_TYPE(x) (((x) & 0xf) << (63-36))
@@ -87,9 +88,6 @@ static inline void ppc_msgsync(void)
#endif /* CONFIG_PPC_BOOK3S */
-extern void doorbell_global_ipi(int cpu);
-extern void doorbell_core_ipi(int cpu);
-extern int doorbell_try_core_ipi(int cpu);
extern void doorbell_exception(struct pt_regs *regs);
static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag)
@@ -100,4 +98,59 @@ static inline void ppc_msgsnd(enum ppc_dbell type, u32 flags, u32 tag)
_ppc_msgsnd(msg);
}
+/*
+ * Doorbells must only be used if CPU_FTR_DBELL is available.
+ * msgsnd is used in HV, and msgsndp is used in !HV.
+ *
+ * These should be used by platform code that is aware of restrictions.
+ * Other arch code should use ->cause_ipi.
+ *
+ * doorbell_global_ipi() sends a dbell to any target CPU.
+ * Must be used only by architectures that address msgsnd target
+ * by PIR/get_hard_smp_processor_id.
+ */
+static inline void doorbell_global_ipi(int cpu)
+{
+ u32 tag = get_hard_smp_processor_id(cpu);
+
+ kvmppc_set_host_ipi(cpu);
+ /* Order previous accesses vs. msgsnd, which is treated as a store */
+ ppc_msgsnd_sync();
+ ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
+}
+
+/*
+ * doorbell_core_ipi() sends a dbell to a target CPU in the same core.
+ * Must be used only by architectures that address msgsnd target
+ * by TIR/cpu_thread_in_core.
+ */
+static inline void doorbell_core_ipi(int cpu)
+{
+ u32 tag = cpu_thread_in_core(cpu);
+
+ kvmppc_set_host_ipi(cpu);
+ /* Order previous accesses vs. msgsnd, which is treated as a store */
+ ppc_msgsnd_sync();
+ ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
+}
+
+/*
+ * Attempt to cause a core doorbell if destination is on the same core.
+ * Returns 1 on success, 0 on failure.
+ */
+static inline int doorbell_try_core_ipi(int cpu)
+{
+ int this_cpu = get_cpu();
+ int ret = 0;
+
+ if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) {
+ doorbell_core_ipi(cpu);
+ ret = 1;
+ }
+
+ put_cpu();
+
+ return ret;
+}
+
#endif /* _ASM_POWERPC_DBELL_H */
diff --git a/arch/powerpc/kernel/dbell.c b/arch/powerpc/kernel/dbell.c
index f17ff1200eaa..52680cf07c9d 100644
--- a/arch/powerpc/kernel/dbell.c
+++ b/arch/powerpc/kernel/dbell.c
@@ -18,61 +18,6 @@
#ifdef CONFIG_SMP
-/*
- * Doorbells must only be used if CPU_FTR_DBELL is available.
- * msgsnd is used in HV, and msgsndp is used in !HV.
- *
- * These should be used by platform code that is aware of restrictions.
- * Other arch code should use ->cause_ipi.
- *
- * doorbell_global_ipi() sends a dbell to any target CPU.
- * Must be used only by architectures that address msgsnd target
- * by PIR/get_hard_smp_processor_id.
- */
-void doorbell_global_ipi(int cpu)
-{
- u32 tag = get_hard_smp_processor_id(cpu);
-
- kvmppc_set_host_ipi(cpu);
- /* Order previous accesses vs. msgsnd, which is treated as a store */
- ppc_msgsnd_sync();
- ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
-}
-
-/*
- * doorbell_core_ipi() sends a dbell to a target CPU in the same core.
- * Must be used only by architectures that address msgsnd target
- * by TIR/cpu_thread_in_core.
- */
-void doorbell_core_ipi(int cpu)
-{
- u32 tag = cpu_thread_in_core(cpu);
-
- kvmppc_set_host_ipi(cpu);
- /* Order previous accesses vs. msgsnd, which is treated as a store */
- ppc_msgsnd_sync();
- ppc_msgsnd(PPC_DBELL_MSGTYPE, 0, tag);
-}
-
-/*
- * Attempt to cause a core doorbell if destination is on the same core.
- * Returns 1 on success, 0 on failure.
- */
-int doorbell_try_core_ipi(int cpu)
-{
- int this_cpu = get_cpu();
- int ret = 0;
-
- if (cpumask_test_cpu(cpu, cpu_sibling_mask(this_cpu))) {
- doorbell_core_ipi(cpu);
- ret = 1;
- }
-
- put_cpu();
-
- return ret;
-}
-
void doorbell_exception(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
--
2.23.0
^ permalink raw reply related
* [PATCH 0/3] powerpc/pseries: IPI doorbell improvements
From: Nicholas Piggin @ 2020-06-27 15:04 UTC (permalink / raw)
To: linuxppc-dev
Cc: Nicholas Piggin, kvm-ppc, Anton Blanchard, Cédric Le Goater,
David Gibson
Thanks for the review, I think I incorporated all your comments, I
also did add KVM detection which avoids introducing a performance
regression.
Thanks,
Nick
Nicholas Piggin (3):
powerpc: inline doorbell sending functions
powerpc/pseries: Use doorbells even if XIVE is available
powerpc/pseries: Add KVM guest doorbell restrictions
arch/powerpc/include/asm/dbell.h | 59 +++++++++++++++++++--
arch/powerpc/include/asm/firmware.h | 2 +
arch/powerpc/include/asm/kvm_para.h | 26 ++--------
arch/powerpc/kernel/dbell.c | 55 --------------------
arch/powerpc/platforms/pseries/firmware.c | 14 +++++
arch/powerpc/platforms/pseries/smp.c | 62 ++++++++++++++++-------
6 files changed, 119 insertions(+), 99 deletions(-)
--
2.23.0
^ permalink raw reply
* Re: [PATCH] powerpc/pseries: Use doorbells even if XIVE is available
From: Nicholas Piggin @ 2020-06-27 14:59 UTC (permalink / raw)
To: Cédric Le Goater, linuxppc-dev, Michael Ellerman
Cc: Anton Blanchard, kvm-ppc, David Gibson
In-Reply-To: <af42c250-cf4b-0815-c91c-9363445383e7@kaod.org>
Excerpts from Cédric Le Goater's message of June 26, 2020 5:17 pm:
> Adding David,
>
> On 6/25/20 3:11 AM, Michael Ellerman wrote:
>> Nicholas Piggin <npiggin@gmail.com> writes:
>>> KVM supports msgsndp in guests by trapping and emulating the
>>> instruction, so it was decided to always use XIVE for IPIs if it is
>>> available. However on PowerVM systems, msgsndp can be used and gives
>>> better performance. On large systems, high XIVE interrupt rates can
>>> have sub-linear scaling, and using msgsndp can reduce the load on
>>> the interrupt controller.
>>>
>>> So switch to using core local doorbells even if XIVE is available.
>>> This reduces performance for KVM guests with an SMT topology by
>>> about 50% for ping-pong context switching between SMT vCPUs.
>>
>> You have to take explicit steps to configure KVM in that way with qemu.
>> eg. "qemu .. -smp 8" will give you 8 SMT1 CPUs by default.
>>
>>> An option vector (or dt-cpu-ftrs) could be defined to disable msgsndp
>>> to get KVM performance back.
>
> An option vector would require a PAPR change. Unless the architecture
> reserves some bits for the implementation, but I don't think so. Same
> for CAS.
>
>> Qemu/KVM populates /proc/device-tree/hypervisor, so we *could* look at
>> that. Though adding PowerVM/KVM specific hacks is obviously a very
>> slippery slope.
>
> QEMU could advertise a property "emulated-msgsndp", or something similar,
> which would be interpreted by Linux as a CPU feature and taken into account
> when doing the IPIs.
What I'm going to do is detect KVM here (we already have a KVM detection
test using that dt property). The IPI setup code already has KVM hacks
in it, so I don't really see the problem with puting them behind a KVM
test.
I think doing cpu ftrs or some specific entry for msgsndp in particular
is the right way to go, but in the interests of making existing KVM work
I'll do this.
Thanks,
Nick
^ permalink raw reply
* [PATCH 8/8] mm: move p?d_alloc_track to separate header file
From: Mike Rapoport @ 2020-06-27 14:34 UTC (permalink / raw)
To: linux-kernel
Cc: linux-ia64, linux-sh, Peter Zijlstra, Max Filippov,
Satheesh Rajendran, linux-csky, sparclinux, linux-riscv,
linux-arch, Stephen Rothwell, linux-hexagon, Joerg Roedel,
Mike Rapoport, Abdul Haleem, linux-snps-arc, linux-xtensa,
Joerg Roedel, Arnd Bergmann, linux-s390, linux-um, Steven Rostedt,
linux-m68k, openrisc, Andy Lutomirski, Stafford Horne,
linux-arm-kernel, linux-parisc, linux-mm, linux-mips, linux-alpha,
Andrew Morton, linuxppc-dev, Mike Rapoport
In-Reply-To: <20200627143453.31835-1-rppt@kernel.org>
From: Joerg Roedel <jroedel@suse.de>
The functions are only used in two source files, both residing in mm/
subdirectory, so there is no need for them to be in the global <linux/mm.h>
header. Move them to the new mm/pgalloc-track.h header and include it only
where needed.
[rppt: mv include/linux/pgalloc-track.h mm/]
Link: http://lkml.kernel.org/r/20200609120533.25867-1-joro@8bytes.org
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Abdul Haleem <abdhalee@linux.vnet.ibm.com>
Cc: Satheesh Rajendran <sathnaga@linux.vnet.ibm.com>
Cc: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
---
include/linux/mm.h | 45 ----------------------------------------
mm/ioremap.c | 2 ++
mm/pgalloc-track.h | 51 ++++++++++++++++++++++++++++++++++++++++++++++
mm/vmalloc.c | 1 +
4 files changed, 54 insertions(+), 45 deletions(-)
create mode 100644 mm/pgalloc-track.h
diff --git a/include/linux/mm.h b/include/linux/mm.h
index dc7b87310c10..5e878a3c7c57 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2093,51 +2093,11 @@ static inline pud_t *pud_alloc(struct mm_struct *mm, p4d_t *p4d,
NULL : pud_offset(p4d, address);
}
-static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd,
- unsigned long address,
- pgtbl_mod_mask *mod_mask)
-
-{
- if (unlikely(pgd_none(*pgd))) {
- if (__p4d_alloc(mm, pgd, address))
- return NULL;
- *mod_mask |= PGTBL_PGD_MODIFIED;
- }
-
- return p4d_offset(pgd, address);
-}
-
-static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d,
- unsigned long address,
- pgtbl_mod_mask *mod_mask)
-{
- if (unlikely(p4d_none(*p4d))) {
- if (__pud_alloc(mm, p4d, address))
- return NULL;
- *mod_mask |= PGTBL_P4D_MODIFIED;
- }
-
- return pud_offset(p4d, address);
-}
-
static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
{
return (unlikely(pud_none(*pud)) && __pmd_alloc(mm, pud, address))?
NULL: pmd_offset(pud, address);
}
-
-static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud,
- unsigned long address,
- pgtbl_mod_mask *mod_mask)
-{
- if (unlikely(pud_none(*pud))) {
- if (__pmd_alloc(mm, pud, address))
- return NULL;
- *mod_mask |= PGTBL_PUD_MODIFIED;
- }
-
- return pmd_offset(pud, address);
-}
#endif /* CONFIG_MMU */
#if USE_SPLIT_PTE_PTLOCKS
@@ -2253,11 +2213,6 @@ static inline void pgtable_pte_page_dtor(struct page *page)
((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \
NULL: pte_offset_kernel(pmd, address))
-#define pte_alloc_kernel_track(pmd, address, mask) \
- ((unlikely(pmd_none(*(pmd))) && \
- (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\
- NULL: pte_offset_kernel(pmd, address))
-
#if USE_SPLIT_PMD_PTLOCKS
static struct page *pmd_to_page(pmd_t *pmd)
diff --git a/mm/ioremap.c b/mm/ioremap.c
index 5ee3526f71b8..5fa1ab41d152 100644
--- a/mm/ioremap.c
+++ b/mm/ioremap.c
@@ -13,6 +13,8 @@
#include <linux/export.h>
#include <asm/cacheflush.h>
+#include "pgalloc-track.h"
+
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
static int __read_mostly ioremap_p4d_capable;
static int __read_mostly ioremap_pud_capable;
diff --git a/mm/pgalloc-track.h b/mm/pgalloc-track.h
new file mode 100644
index 000000000000..1dcc865029a2
--- /dev/null
+++ b/mm/pgalloc-track.h
@@ -0,0 +1,51 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_PGALLLC_TRACK_H
+#define _LINUX_PGALLLC_TRACK_H
+
+#if defined(CONFIG_MMU)
+static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd,
+ unsigned long address,
+ pgtbl_mod_mask *mod_mask)
+{
+ if (unlikely(pgd_none(*pgd))) {
+ if (__p4d_alloc(mm, pgd, address))
+ return NULL;
+ *mod_mask |= PGTBL_PGD_MODIFIED;
+ }
+
+ return p4d_offset(pgd, address);
+}
+
+static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d,
+ unsigned long address,
+ pgtbl_mod_mask *mod_mask)
+{
+ if (unlikely(p4d_none(*p4d))) {
+ if (__pud_alloc(mm, p4d, address))
+ return NULL;
+ *mod_mask |= PGTBL_P4D_MODIFIED;
+ }
+
+ return pud_offset(p4d, address);
+}
+
+static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud,
+ unsigned long address,
+ pgtbl_mod_mask *mod_mask)
+{
+ if (unlikely(pud_none(*pud))) {
+ if (__pmd_alloc(mm, pud, address))
+ return NULL;
+ *mod_mask |= PGTBL_PUD_MODIFIED;
+ }
+
+ return pmd_offset(pud, address);
+}
+#endif /* CONFIG_MMU */
+
+#define pte_alloc_kernel_track(pmd, address, mask) \
+ ((unlikely(pmd_none(*(pmd))) && \
+ (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\
+ NULL: pte_offset_kernel(pmd, address))
+
+#endif /* _LINUX_PGALLLC_TRACK_H */
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 5a2b55c8dd9a..5be3cf3b59de 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -41,6 +41,7 @@
#include <asm/shmparam.h>
#include "internal.h"
+#include "pgalloc-track.h"
bool is_vmalloc_addr(const void *x)
{
--
2.26.2
^ permalink raw reply related
* [PATCH 7/8] mm: move lib/ioremap.c to mm/
From: Mike Rapoport @ 2020-06-27 14:34 UTC (permalink / raw)
To: linux-kernel
Cc: linux-ia64, linux-sh, Peter Zijlstra, Max Filippov,
Satheesh Rajendran, linux-csky, sparclinux, linux-riscv,
linux-arch, Stephen Rothwell, linux-hexagon, Joerg Roedel,
Mike Rapoport, Abdul Haleem, linux-snps-arc, linux-xtensa,
Arnd Bergmann, linux-s390, linux-um, Steven Rostedt, linux-m68k,
openrisc, Andy Lutomirski, Stafford Horne, linux-arm-kernel,
linux-parisc, linux-mm, linux-mips, linux-alpha, Andrew Morton,
linuxppc-dev, Mike Rapoport
In-Reply-To: <20200627143453.31835-1-rppt@kernel.org>
From: Mike Rapoport <rppt@linux.ibm.com>
The functionality in lib/ioremap.c deals with pagetables, vmalloc and
caches, so it naturally belongs to mm/
Moving it there will also allow declaring p?d_alloc_track functions in an
header file inside mm/ rather than having those declarations in
include/linux/mm.h
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Mike Rapoport <rppt@linux.ibm.com>
---
lib/Makefile | 1 -
mm/Makefile | 2 +-
{lib => mm}/ioremap.c | 0
3 files changed, 1 insertion(+), 2 deletions(-)
rename {lib => mm}/ioremap.c (100%)
diff --git a/lib/Makefile b/lib/Makefile
index b1c42c10073b..5f9384adde9c 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -37,7 +37,6 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
nmi_backtrace.o nodemask.o win_minmax.o memcat_p.o
lib-$(CONFIG_PRINTK) += dump_stack.o
-lib-$(CONFIG_MMU) += ioremap.o
lib-$(CONFIG_SMP) += cpumask.o
lib-y += kobject.o klist.o
diff --git a/mm/Makefile b/mm/Makefile
index 6e9d46b2efc9..d5649f1c12c0 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -38,7 +38,7 @@ mmu-y := nommu.o
mmu-$(CONFIG_MMU) := highmem.o memory.o mincore.o \
mlock.o mmap.o mmu_gather.o mprotect.o mremap.o \
msync.o page_vma_mapped.o pagewalk.o \
- pgtable-generic.o rmap.o vmalloc.o
+ pgtable-generic.o rmap.o vmalloc.o ioremap.o
ifdef CONFIG_CROSS_MEMORY_ATTACH
diff --git a/lib/ioremap.c b/mm/ioremap.c
similarity index 100%
rename from lib/ioremap.c
rename to mm/ioremap.c
--
2.26.2
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox