[PATCH 6.0 098/148] qed: allow sleep in qed_mcp_trace_dump()

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

From: Caleb Sander <csander@purestorage.com>

[ Upstream commit 5401c3e0992860b11fb4b25796e4c4f1921740df ]

By default, qed_mcp_cmd_and_union() delays 10us at a time in a loop
that can run 500K times, so calls to qed_mcp_nvm_rd_cmd()
may block the current thread for over 5s.
We observed thread scheduling delays over 700ms in production,
with stacktraces pointing to this code as the culprit.

qed_mcp_trace_dump() is called from ethtool, so sleeping is permitted.
It already can sleep in qed_mcp_halt(), which calls qed_mcp_cmd().
Add a "can sleep" parameter to qed_find_nvram_image() and
qed_nvram_read() so they can sleep during qed_mcp_trace_dump().
qed_mcp_trace_get_meta_info() and qed_mcp_trace_read_meta(),
called only by qed_mcp_trace_dump(), allow these functions to sleep.
I can't tell if the other caller (qed_grc_dump_mcp_hw_dump()) can sleep,
so keep b_can_sleep set to false when it calls these functions.

An example stacktrace from a custom warning we added to the kernel
showing a thread that has not scheduled despite long needing resched:
[ 2745.362925,17] ------------[ cut here ]------------
[ 2745.362941,17] WARNING: CPU: 23 PID: 5640 at arch/x86/kernel/irq.c:233 do_IRQ+0x15e/0x1a0()
[ 2745.362946,17] Thread not rescheduled for 744 ms after irq 99
[ 2745.362956,17] Modules linked in: ...
[ 2745.363339,17] CPU: 23 PID: 5640 Comm: lldpd Tainted: P           O    4.4.182+ #202104120910+6d1da174272d.61x
[ 2745.363343,17] Hardware name: FOXCONN MercuryB/Quicksilver Controller, BIOS H11P1N09 07/08/2020
[ 2745.363346,17]  0000000000000000 ffff885ec07c3ed8 ffffffff8131eb2f ffff885ec07c3f20
[ 2745.363358,17]  ffffffff81d14f64 ffff885ec07c3f10 ffffffff81072ac2 ffff88be98ed0000
[ 2745.363369,17]  0000000000000063 0000000000000174 0000000000000074 0000000000000000
[ 2745.363379,17] Call Trace:
[ 2745.363382,17]  <IRQ>  [<ffffffff8131eb2f>] dump_stack+0x8e/0xcf
[ 2745.363393,17]  [<ffffffff81072ac2>] warn_slowpath_common+0x82/0xc0
[ 2745.363398,17]  [<ffffffff81072b4c>] warn_slowpath_fmt+0x4c/0x50
[ 2745.363404,17]  [<ffffffff810d5a8e>] ? rcu_irq_exit+0xae/0xc0
[ 2745.363408,17]  [<ffffffff817c99fe>] do_IRQ+0x15e/0x1a0
[ 2745.363413,17]  [<ffffffff817c7ac9>] common_interrupt+0x89/0x89
[ 2745.363416,17]  <EOI>  [<ffffffff8132aa74>] ? delay_tsc+0x24/0x50
[ 2745.363425,17]  [<ffffffff8132aa04>] __udelay+0x34/0x40
[ 2745.363457,17]  [<ffffffffa04d45ff>] qed_mcp_cmd_and_union+0x36f/0x7d0 [qed]
[ 2745.363473,17]  [<ffffffffa04d5ced>] qed_mcp_nvm_rd_cmd+0x4d/0x90 [qed]
[ 2745.363490,17]  [<ffffffffa04e1dc7>] qed_mcp_trace_dump+0x4a7/0x630 [qed]
[ 2745.363504,17]  [<ffffffffa04e2556>] ? qed_fw_asserts_dump+0x1d6/0x1f0 [qed]
[ 2745.363520,17]  [<ffffffffa04e4ea7>] qed_dbg_mcp_trace_get_dump_buf_size+0x37/0x80 [qed]
[ 2745.363536,17]  [<ffffffffa04ea881>] qed_dbg_feature_size+0x61/0xa0 [qed]
[ 2745.363551,17]  [<ffffffffa04eb427>] qed_dbg_all_data_size+0x247/0x260 [qed]
[ 2745.363560,17]  [<ffffffffa0482c10>] qede_get_regs_len+0x30/0x40 [qede]
[ 2745.363566,17]  [<ffffffff816c9783>] ethtool_get_drvinfo+0xe3/0x190
[ 2745.363570,17]  [<ffffffff816cc152>] dev_ethtool+0x1362/0x2140
[ 2745.363575,17]  [<ffffffff8109bcc6>] ? finish_task_switch+0x76/0x260
[ 2745.363580,17]  [<ffffffff817c2116>] ? __schedule+0x3c6/0x9d0
[ 2745.363585,17]  [<ffffffff810dbd50>] ? hrtimer_start_range_ns+0x1d0/0x370
[ 2745.363589,17]  [<ffffffff816c1e5b>] ? dev_get_by_name_rcu+0x6b/0x90
[ 2745.363594,17]  [<ffffffff816de6a8>] dev_ioctl+0xe8/0x710
[ 2745.363599,17]  [<ffffffff816a58a8>] sock_do_ioctl+0x48/0x60
[ 2745.363603,17]  [<ffffffff816a5d87>] sock_ioctl+0x1c7/0x280
[ 2745.363608,17]  [<ffffffff8111f393>] ? seccomp_phase1+0x83/0x220
[ 2745.363612,17]  [<ffffffff811e3503>] do_vfs_ioctl+0x2b3/0x4e0
[ 2745.363616,17]  [<ffffffff811e3771>] SyS_ioctl+0x41/0x70
[ 2745.363619,17]  [<ffffffff817c6ffe>] entry_SYSCALL_64_fastpath+0x1e/0x79
[ 2745.363622,17] ---[ end trace f6954aa440266421 ]---

Fixes: c965db4446291 ("qed: Add support for debug data collection")
Signed-off-by: Caleb Sander <csander@purestorage.com>
Acked-by: Alok Prasad <palok@marvell.com>
Link: https://lore.kernel.org/r/20230103233021.1457646-1-csander@purestorage.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/qlogic/qed/qed_debug.c | 28 +++++++++++++++------
 1 file changed, 20 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c
index 86ecb080b153..cdcead614e9f 100644
--- a/drivers/net/ethernet/qlogic/qed/qed_debug.c
+++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c
@@ -1832,7 +1832,8 @@ static enum dbg_status qed_find_nvram_image(struct qed_hwfn *p_hwfn,
 					    struct qed_ptt *p_ptt,
 					    u32 image_type,
 					    u32 *nvram_offset_bytes,
-					    u32 *nvram_size_bytes)
+					    u32 *nvram_size_bytes,
+					    bool b_can_sleep)
 {
 	u32 ret_mcp_resp, ret_mcp_param, ret_txn_size;
 	struct mcp_file_att file_att;
@@ -1846,7 +1847,8 @@ static enum dbg_status qed_find_nvram_image(struct qed_hwfn *p_hwfn,
 					&ret_mcp_resp,
 					&ret_mcp_param,
 					&ret_txn_size,
-					(u32 *)&file_att, false);
+					(u32 *)&file_att,
+					b_can_sleep);
 
 	/* Check response */
 	if (nvm_result || (ret_mcp_resp & FW_MSG_CODE_MASK) !=
@@ -1873,7 +1875,9 @@ static enum dbg_status qed_find_nvram_image(struct qed_hwfn *p_hwfn,
 static enum dbg_status qed_nvram_read(struct qed_hwfn *p_hwfn,
 				      struct qed_ptt *p_ptt,
 				      u32 nvram_offset_bytes,
-				      u32 nvram_size_bytes, u32 *ret_buf)
+				      u32 nvram_size_bytes,
+				      u32 *ret_buf,
+				      bool b_can_sleep)
 {
 	u32 ret_mcp_resp, ret_mcp_param, ret_read_size, bytes_to_copy;
 	s32 bytes_left = nvram_size_bytes;
@@ -1899,7 +1903,7 @@ static enum dbg_status qed_nvram_read(struct qed_hwfn *p_hwfn,
 				       &ret_mcp_resp,
 				       &ret_mcp_param, &ret_read_size,
 				       (u32 *)((u8 *)ret_buf + read_offset),
-				       false))
+				       b_can_sleep))
 			return DBG_STATUS_NVRAM_READ_FAILED;
 
 		/* Check response */
@@ -3380,7 +3384,8 @@ static u32 qed_grc_dump_mcp_hw_dump(struct qed_hwfn *p_hwfn,
 				      p_ptt,
 				      NVM_TYPE_HW_DUMP_OUT,
 				      &hw_dump_offset_bytes,
-				      &hw_dump_size_bytes);
+				      &hw_dump_size_bytes,
+				      false);
 	if (status != DBG_STATUS_OK)
 		return 0;
 
@@ -3397,7 +3402,9 @@ static u32 qed_grc_dump_mcp_hw_dump(struct qed_hwfn *p_hwfn,
 		status = qed_nvram_read(p_hwfn,
 					p_ptt,
 					hw_dump_offset_bytes,
-					hw_dump_size_bytes, dump_buf + offset);
+					hw_dump_size_bytes,
+					dump_buf + offset,
+					false);
 		if (status != DBG_STATUS_OK) {
 			DP_NOTICE(p_hwfn,
 				  "Failed to read MCP HW Dump image from NVRAM\n");
@@ -4123,7 +4130,9 @@ static enum dbg_status qed_mcp_trace_get_meta_info(struct qed_hwfn *p_hwfn,
 	return qed_find_nvram_image(p_hwfn,
 				    p_ptt,
 				    nvram_image_type,
-				    trace_meta_offset, trace_meta_size);
+				    trace_meta_offset,
+				    trace_meta_size,
+				    true);
 }
 
 /* Reads the MCP Trace meta data from NVRAM into the specified buffer */
@@ -4139,7 +4148,10 @@ static enum dbg_status qed_mcp_trace_read_meta(struct qed_hwfn *p_hwfn,
 	/* Read meta data from NVRAM */
 	status = qed_nvram_read(p_hwfn,
 				p_ptt,
-				nvram_offset_in_bytes, size_in_bytes, buf);
+				nvram_offset_in_bytes,
+				size_in_bytes,
+				buf,
+				true);
 	if (status != DBG_STATUS_OK)
 		return status;
 
-- 
2.35.1